© 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. 7511
    Prev
    Next
    INDEX
    Explanations

    Precision and accuracy

    np_max-act · gemini-2.0-flash

    The neuron is tuned to pick out numeric expressions—digits, decimals, and scientific‐notation components—in technical text.

    oai_token-act-pair · o4-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
     continuous
    -0.07
    Continuous
    -0.07
     nid
    -0.07
     rude
    -0.07
     Continuous
    -0.06
    appear
    -0.06
     agility
    -0.06
    Todd
    -0.06
    datap
    -0.06
    _protocol
    -0.06
    POSITIVE LOGITS
    Abort
    0.06
    FAILURE
    0.06
     campaigns
    0.06
     Loose
    0.06
     outros
    0.06
    orthand
    0.06
     Wikip
    0.06
     türü
    0.06
     brands
    0.06
     accord
    0.06
    Activations Density 0.018%

    No Known Activations