© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109023
    Prev
    Next
    INDEX
    Explanations

    tf

    np_max-act · gemini-2.0-flash

    Same activations, but with all zeros filtered out: <start> tf 3.904296875 keras 0.80712890625 <end> <start> tf 3.890625 <end> <start> tf 3.830078125 <end> <start> tf 0.98779296875 <end> <start> tf 3.822265625 <end> <start> tf 3.8046875 <end> <start> tf 3.794921875 <end> <start> tf 3.79296875 <end> Explanation of neuron 4 behavior: the main thing this neuron does is find mentions of the TensorFlow library (e.g. the tokens “tf” and “keras”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    code snippets related to neural network architectures.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ystate
    -0.06
    "/>.</
    -0.06
    ã
    -0.06
     crushing
    -0.06
    (area
    -0.06
    ایی
    -0.06
    Japgolly
    -0.06
    riteria
    -0.06
     в
    -0.06
    ailer
    -0.06
    POSITIVE LOGITS
     cartoons
    0.07
    ，↵↵
    0.06
    lectual
    0.06
    .Ignore
    0.06
    _MOVE
    0.06
    ược
    0.06
     blasph
    0.06
    methodVisitor
    0.06
     शर
    0.06
    เวลา
    0.06
    Activations Density 0.000%

    No Known Activations