© 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
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 105277
    Prev
    Next
    INDEX
    Explanations

    policy

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     twitch
    -0.07
    _off
    -0.06
     Streams
    -0.06
    SEQUENTIAL
    -0.06
    具体
    -0.06
     grapes
    -0.06
     jednoho
    -0.06
     Hipp
    -0.06
    OrCreate
    -0.06
    ріш
    -0.06
    POSITIVE LOGITS
     Proto
    0.06
    .enable
    0.06
    (active
    0.06
    UPER
    0.06
    ッチ
    0.06
     проц
    0.06
    ,更
    0.06
    ogeneous
    0.06
    TEGR
    0.06
    (pow
    0.06
    Activations Density 0.016%

    No Known Activations