© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 18029
    Prev
    Next
    INDEX
    Explanations

    - and 00

    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
     sympathetic
    -0.07
    Carousel
    -0.07
    Titles
    -0.07
    716
    -0.07
    Jon
    -0.06
    /grpc
    -0.06
    nicas
    -0.06
    ордин
    -0.06
    compet
    -0.06
    �乐
    -0.06
    POSITIVE LOGITS
     opposing
    0.07
     HOME
    0.06
     ⓘ
    0.06
     még
    0.06
     nichts
    0.06
     куст
    0.06
     uz
    0.06
     gece
    0.06
     peu
    0.06
    (sess
    0.06
    Activations Density 0.002%

    No Known Activations