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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58153
    Prev
    Next
    INDEX
    Explanations

    help/assistance

    np_max-act · gemini-2.0-flash

    This neuron responds to the assistant’s offers of help, specifically activating on the word “assist.”

    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
    =Integer
    -0.06
     эта
    -0.06
    лів
    -0.06
    zan
    -0.06
    زة
    -0.06
    frica
    -0.06
    능
    -0.06
     conductivity
    -0.06
     Nuclear
    -0.06
     [<
    -0.06
    POSITIVE LOGITS
    .entrySet
    0.06
    onym
    0.06
    (SQLException
    0.06
     спри
    0.06
    uned
    0.06
    ="'+
    0.06
     أم
    0.06
     Reply
    0.06
    -",
    0.06
     Officer
    0.06
    Activations Density 0.017%

    No Known Activations