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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 20268
    Prev
    Next
    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash

    decimal floating-point numbers (numbers with a fractional part like 6.49609375).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     ува
    -0.06
     jednotlivých
    -0.06
     aggregated
    -0.06
    nač
    -0.06
    emplates
    -0.06
     Commons
    -0.06
     weekends
    -0.06
    abilia
    -0.06
     autre
    -0.06
    poč
    -0.06
    POSITIVE LOGITS
    _DH
    0.07
     militia
    0.06
     Ả
    0.06
     girl
    0.06
     çeşitli
    0.06
    _YELLOW
    0.06
     mineral
    0.06
    policy
    0.06
     missionary
    0.06
    λία
    0.06
    Activations Density 0.001%

    No Known Activations