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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 100191
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    code snippets related to reading JSON files in Python, including handling UTF-8 encoding.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron never activates and thus doesn’t detect any particular textual feature.

    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
     rash
    -0.07
     spor
    -0.07
     Werk
    -0.06
    firstname
    -0.06
    <System
    -0.06
    gether
    -0.06
    223
    -0.06
     GPUs
    -0.06
     werk
    -0.06
     NAN
    -0.06
    POSITIVE LOGITS
    contents
    0.07
     effort
    0.07
    0.07
    الد
    0.07
     засід
    0.06
     Dhabi
    0.06
     Empty
    0.06
    .bid
    0.06
    cord
    0.06
    nila
    0.06
    Activations Density 0.016%

    No Known Activations