© 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
    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. 53799
    Prev
    Next
    INDEX
    Explanations

    fact

    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
     phantom
    -0.07
    관
    -0.07
     pager
    -0.07
    Re
    -0.06
     Pool
    -0.06
    facet
    -0.06
     Designs
    -0.06
     Fighters
    -0.06
     cả
    -0.06
    Instruction
    -0.06
    POSITIVE LOGITS
    .ng
    0.07
    ulu
    0.07
    ổng
    0.07
    戲
    0.06
    "name
    0.06
    .updated
    0.06
     ویکی
    0.06
     needless
    0.06
    lett
    0.06
    зи
    0.06
    Activations Density 0.004%

    No Known Activations