Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 77474
    Prev
    Next
    INDEX
    Explanations

    id

    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
     handguns
    -0.06
    ascimento
    -0.06
    Legacy
    -0.06
     member
    -0.06
    解决
    -0.06
    Choice
    -0.06
    _team
    -0.06
    zení
    -0.06
     smrti
    -0.06
    istan
    -0.06
    POSITIVE LOGITS
    tatus
    0.07
    станов
    0.07
    .'"↵↵
    0.07
    :["
    0.06
     dân
    0.06
     cinemas
    0.06
     DIFF
    0.06
    riott
    0.06
     locally
    0.06
    uspended
    0.06
    Activations Density 0.002%

    No Known Activations