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. 123430
    Prev
    Next
    INDEX
    Explanations

    technology

    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
     silah
    -0.08
    enemy
    -0.07
    ascade
    -0.07
    asString
    -0.07
     глав
    -0.06
     designated
    -0.06
     irregular
    -0.06
     excursion
    -0.06
    _message
    -0.06
    _BINDING
    -0.06
    POSITIVE LOGITS
    [].
    0.07
    ystals
    0.06
    olving
    0.06
    utura
    0.06
    /the
    0.06
     Можно
    0.05
     youre
    0.05
     чим
    0.05
    ingly
    0.05
    谁
    0.05
    Activations Density 0.329%

    No Known Activations