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. 111096
    Prev
    Next
    INDEX
    Explanations

    seldom

    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
     environmental
    -0.07
     borne
    -0.07
    _\
    -0.06
    -induced
    -0.06
    ί
    -0.06
    .tw
    -0.06
     sesión
    -0.06
     modes
    -0.06
     kanı
    -0.06
    ูม
    -0.06
    POSITIVE LOGITS
    ,K
    0.07
     PROF
    0.07
    _UNITS
    0.07
    LAG
    0.06
     čtyři
    0.06
    ноз
    0.06
     وسلم
    0.06
     وش
    0.06
     Ast
    0.06
    اوت
    0.06
    Activations Density 0.197%

    No Known Activations