© 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. 52982
    Prev
    Next
    INDEX
    Explanations

    Poll

    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
     Henry
    -0.08
     ships
    -0.08
     ingredients
    -0.07
     stages
    -0.07
    KEN
    -0.07
     duct
    -0.07
    ат
    -0.07
     blade
    -0.07
     diagonal
    -0.07
    Craft
    -0.07
    POSITIVE LOGITS
     Poll
    0.10
    Poll
    0.10
     polling
    0.09
     poll
    0.09
     polls
    0.09
    all
    0.08
    All
    0.07
    ALL
    0.07
    LL
    0.07
    ll
    0.07
    Activations Density 0.003%

    No Known Activations