© 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
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 93405
    Prev
    Next
    INDEX
    Explanations

    letter analysis

    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
     мир
    -0.07
    TRIES
    -0.07
     Ras
    -0.06
    _os
    -0.06
     DOMAIN
    -0.06
    ascus
    -0.06
     Koh
    -0.06
     declarations
    -0.06
     unfit
    -0.06
     rhyme
    -0.06
    POSITIVE LOGITS
    -po
    0.06
    ín
    0.06
    كة
    0.06
    filtro
    0.06
    关键
    0.06
     LIABILITY
    0.06
    %D
    0.06
    _VOID
    0.06
    TOTYPE
    0.06
    033
    0.06
    Activations Density 0.007%

    No Known Activations