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. 15-RESID-POST-AA
    6. 80013
    Prev
    Next
    INDEX
    Explanations

    honesty

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lamış
    -0.07
     Basic
    -0.07
     vocab
    -0.06
    ís
    -0.06
    樓
    -0.06
    局
    -0.06
    "<?
    -0.06
    CUS
    -0.06
    卓
    -0.06
    ?↵↵↵↵↵↵
    -0.06
    POSITIVE LOGITS
    .Address
    0.07
     Modify
    0.06
    arger
    0.06
    レビ
    0.06
     Veterinary
    0.06
    LLU
    0.06
    buyer
    0.06
    .getName
    0.06
     rámci
    0.06
     rude
    0.06
    Activations Density 0.012%

    No Known Activations