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. 111117
    Prev
    Next
    INDEX
    Explanations

    bible

    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
    _oper
    -0.07
     Strauss
    -0.06
    zos
    -0.06
    ért
    -0.06
    anked
    -0.06
    Fecha
    -0.06
    -be
    -0.06
    irate
    -0.06
     Millions
    -0.06
     Fill
    -0.06
    POSITIVE LOGITS
    ,X
    0.08
    _boost
    0.07
    bound
    0.07
     vampire
    0.07
     glVertex
    0.07
    spell
    0.06
    خو
    0.06
    getChild
    0.06
     αυτό
    0.06
    |^
    0.06
    Activations Density 0.017%

    No Known Activations