© 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. 104825
    Prev
    Next
    INDEX
    Explanations

    dynamically

    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
     copies
    -0.07
    状態
    -0.07
    Won
    -0.07
    -sn
    -0.07
     interrupted
    -0.07
     threshold
    -0.06
     disple
    -0.06
    alia
    -0.06
    เหน
    -0.06
    üssen
    -0.06
    POSITIVE LOGITS
    ishly
    0.08
     Bek
    0.07
     "}↵
    0.07
    ":"","
    0.06
     động
    0.06
    >";
    ↵
    0.06
    Wildcard
    0.06
     Shan
    0.06
     ATL
    0.06
    745
    0.06
    Activations Density 0.009%

    No Known Activations