© 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
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 28302
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     punct
    -0.07
     restaurant
    -0.06
    ,…
    -0.06
    енно
    -0.06
     ingredients
    -0.06
     Blockchain
    -0.06
    _matches
    -0.06
    онд
    -0.06
     температу
    -0.06
    .AlertDialog
    -0.06
    POSITIVE LOGITS
     linking
    0.07
    )
    ↵
    ↵
    ↵
    0.06
    umhur
    0.06
    Der
    0.06
    ObjectId
    0.06
    ونه
    0.06
     khung
    0.06
     Huckabee
    0.06
    (KeyEvent
    0.06
     вір
    0.06
    Activations Density 0.155%

    No Known Activations