© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 62829
    Prev
    Next
    INDEX
    Explanations

    min

    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
    頭
    -0.07
     AD
    -0.07
    LAST
    -0.07
    upert
    -0.06
    ItemType
    -0.06
    APH
    -0.06
     Dự
    -0.06
    _parameter
    -0.06
    itives
    -0.06
    DEX
    -0.06
    POSITIVE LOGITS
    (HttpServletRequest
    0.07
     ott
    0.06
    .createElement
    0.06
     useNewUrlParser
    0.06
    ittal
    0.06
     симптом
    0.06
     entrepreneur
    0.06
    mí
    0.06
     getAll
    0.06
     мас
    0.06
    Activations Density 0.000%

    No Known Activations