© 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. 15-RESID-POST-AA
    11. 115320
    Prev
    Next
    INDEX
    Explanations

    of

    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
     Enlight
    -0.07
    كال
    -0.06
     Españ
    -0.06
    .',
↵
    -0.06
    acf
    -0.06
    ,but
    -0.06
     ic
    -0.06
     VAR
    -0.06
     luận
    -0.06
     Şampiyon
    -0.06
    POSITIVE LOGITS
    renderer
    0.07
    _DISPLAY
    0.07
    ोज
    0.07
    latest
    0.06
    _integral
    0.06
    Macro
    0.06
    minating
    0.06
    gzip
    0.06
     autoFocus
    0.06
    ASTE
    0.06
    Activations Density 0.014%

    No Known Activations