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. 83821
    Prev
    Next
    INDEX
    Explanations

    Web addresses

    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
    浴
    -0.07
     bm
    -0.07
    .brand
    -0.07
    stdexcept
    -0.07
    imar
    -0.06
    ิทยาศาสตร
    -0.06
    aravel
    -0.06
     несп
    -0.06
     투
    -0.06
    Remark
    -0.06
    POSITIVE LOGITS
    üme
    0.07
    léd
    0.06
    Coordinates
    0.06
     Jens
    0.06
     ={↵
    0.06
    quests
    0.06
    _enum
    0.06
    .prof
    0.06
    alternate
    0.06
     Seven
    0.06
    Activations Density 0.017%

    No Known Activations