© 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. 88238
    Prev
    Next
    INDEX
    Explanations

    scientific models and examples

    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
    /GL
    -0.07
     Robotics
    -0.07
    Pokud
    -0.06
     iris
    -0.06
    -toggler
    -0.06
    tim
    -0.06
    번호
    -0.06
     ABC
    -0.06
     bao
    -0.06
    -pound
    -0.06
    POSITIVE LOGITS
     SOUR
    0.06
    BUILD
    0.06
     капіт
    0.06
    AVING
    0.06
     Unexpected
    0.06
     LOOK
    0.06
     Prest
    0.06
    izacao
    0.05
     χα
    0.05
    PRICE
    0.05
    Activations Density 0.163%

    No Known Activations