© 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. 7-RESID-POST-AA
    11. 23229
    Prev
    Next
    INDEX
    Explanations

    Performance enhancement/unfair advantage

    np_max-act · gemini-2.0-flash

    Mentions of prohibited or performance-enhancing drugs, medications, doping and related regulatory terms (e.g., therapeutic use exemptions and testing) in sports contexts.

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    сяг
    -0.07
    资金
    -0.07
    藝
    -0.06
    rays
    -0.06
    quotelev
    -0.06
    ผล
    -0.06
    externalActionCode
    -0.06
    ραβ
    -0.06
    itors
    -0.06
    -funded
    -0.06
    POSITIVE LOGITS
    _master
    0.06
     Maurice
    0.06
    .cpp
    0.06
    _jump
    0.06
    parms
    0.06
     endregion
    0.06
     좋아
    0.06
    pecting
    0.06
     skyline
    0.06
     (*.
    0.06
    Activations Density 0.181%

    No Known Activations