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. 104374
    Prev
    Next
    INDEX
    Explanations

    legal, court cases

    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
    antar
    -0.06
     advers
    -0.06
     Westminster
    -0.06
     squir
    -0.06
    .mysql
    -0.06
     werk
    -0.06
    .currentTime
    -0.06
     oppon
    -0.06
     manner
    -0.06
     Muham
    -0.06
    POSITIVE LOGITS
    -Identifier
    0.07
     lương
    0.07
     Enjoy
    0.06
    ‐‐
    0.06
    (ec
    0.06
     Lit
    0.06
    ('@
    0.06
     sortBy
    0.06
     rue
    0.06
     mezun
    0.06
    Activations Density 0.009%

    No Known Activations