© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 19881
    Prev
    Next
    INDEX
    Explanations

    often

    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
    >",
    -0.06
    альным
    -0.06
    剂
    -0.06
     �
    -0.06
    "]["
    -0.06
    .camera
    -0.06
     외국
    -0.06
    γκο
    -0.06
    ertainty
    -0.06
     lời
    -0.06
    POSITIVE LOGITS
     seiz
    0.07
     vu
    0.07
    manifest
    0.06
     CMP
    0.06
     господар
    0.06
    _cons
    0.06
    *****↵
    0.06
     Finland
    0.06
    読
    0.06
     fours
    0.06
    Activations Density 0.050%

    No Known Activations