Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22220
    Prev
    Next
    INDEX
    Explanations

    xl

    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
     signify
    -0.07
     мам
    -0.07
    quares
    -0.07
     يش
    -0.07
    ░
    -0.06
    smouth
    -0.06
    .mask
    -0.06
    oga
    -0.06
     SearchResult
    -0.06
     نيز
    -0.06
    POSITIVE LOGITS
    zl
    0.07
     банку
    0.06
     SOLD
    0.06
     disruptions
    0.06
     ΚΑΙ
    0.06
    prises
    0.06
     Dix
    0.06
    陷
    0.06
    突
    0.06
    asc
    0.06
    Activations Density 0.001%

    No Known Activations