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. 11-RESID-POST-AA
    6. 21765
    Prev
    Next
    INDEX
    Explanations

    Numerical digit validation

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تو
    -0.08
    leted
    -0.07
     BU
    -0.07
    FU
    -0.07
    wash
    -0.07
    bed
    -0.07
    wives
    -0.07
    buf
    -0.07
    ickým
    -0.07
     INDEX
    -0.07
    POSITIVE LOGITS
    (f
    0.07
     indoor
    0.06
    基地
    0.06
     impeccable
    0.06
     الجن
    0.06
     epidemic
    0.06
    ___
    0.06
    EGA
    0.06
    parcel
    0.05
     uprising
    0.05
    Activations Density 0.017%

    No Known Activations