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. 27-RESID-POST-AA
    6. 9312
    Prev
    Next
    INDEX
    Explanations

    panel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queries
    -0.07
     court
    -0.07
     retirement
    -0.07
     complaints
    -0.07
     southern
    -0.07
     temporary
    -0.07
     सब
    -0.07
     Women
    -0.06
    _client
    -0.06
     Reaction
    -0.06
    POSITIVE LOGITS
    tam
    0.06
    entai
    0.06
    creature
    0.06
     개최
    0.06
    enguins
    0.06
     �
    0.06
    cps
    0.06
    &P
    0.06
    Pres
    0.06
     feas
    0.06
    Activations Density 0.004%

    No Known Activations