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. 19-RESID-POST-AA
    6. 105111
    Prev
    Next
    INDEX
    Explanations

    Negative statements

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _field
    -0.07
    िजल
    -0.07
    Bubble
    -0.07
    _CACHE
    -0.06
     SER
    -0.06
    -prop
    -0.06
    KEN
    -0.06
    Live
    -0.06
     Wen
    -0.06
     dude
    -0.06
    POSITIVE LOGITS
    +/
    0.08
     nastav
    0.08
     scr
    0.06
     чоловік
    0.06
    読
    0.06
     Latin
    0.06
    -Nazi
    0.06
    ेय
    0.06
     ayrıntı
    0.06
    phin
    0.06
    Activations Density 0.003%

    No Known Activations