Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 50558
    Prev
    Next
    INDEX
    Explanations

    completing tasks

    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
     راه
    -0.06
    _base
    -0.06
     ITS
    -0.06
     conn
    -0.06
    Sugar
    -0.06
    aming
    -0.06
     Sugar
    -0.06
    FD
    -0.06
    ancial
    -0.06
    ในการ
    -0.06
    POSITIVE LOGITS
    lí
    0.06
     pís
    0.06
    ुष
    0.06
     Prepared
    0.06
    ào
    0.06
    九
    0.06
     입니다
    0.06
    ::|
    0.06
    उत
    0.06
    165
    0.06
    Activations Density 0.044%

    No Known Activations