© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 31271
    Prev
    Next
    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Πλη
    -0.07
    .pointer
    -0.06
    _node
    -0.06
    atoon
    -0.06
    Marker
    -0.06
    Newton
    -0.06
    INGER
    -0.06
    编辑
    -0.06
     Forgotten
    -0.06
    Occ
    -0.06
    POSITIVE LOGITS
    ":{↵
    0.08
     angi
    0.08
     {↵
    0.07
     використов
    0.07
     thuisontvangst
    0.07
    ":{"
    0.07
     @{↵
    0.06
     reh
    0.06
    <header
    0.06
     \<
    0.06
    Activations Density 0.013%

    No Known Activations