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. 104131
    Prev
    Next
    INDEX
    Explanations

    book/document descriptions

    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
    과정
    -0.07
    ères
    -0.06
    >f
    -0.06
    .Utility
    -0.06
    adol
    -0.06
    uye
    -0.06
    >p
    -0.06
    ежду
    -0.06
    اوه
    -0.06
    ीटर
    -0.05
    POSITIVE LOGITS
    ucceed
    0.07
    Chance
    0.07
     Pointer
    0.07
     dilig
    0.07
     L
    0.07
     WAY
    0.07
    255
    0.07
     จะ
    0.06
    453
    0.06
    lbs
    0.06
    Activations Density 0.008%

    No Known Activations