Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 80715
    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_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
     mothers
    -0.07
     Všech
    -0.07
    eto
    -0.07
    Register
    -0.07
     penned
    -0.07
     Pollution
    -0.06
     deterioration
    -0.06
     Ref
    -0.06
     bak
    -0.06
    <Client
    -0.06
    POSITIVE LOGITS
    schema
    0.06
    (origin
    0.06
    /browser
    0.06
     SQLiteDatabase
    0.06
    .throw
    0.06
    ,即
    0.06
    .'/
    0.06
    -you
    0.06
     близько
    0.06
    .FormStartPosition
    0.06
    Activations Density 0.003%

    No Known Activations