© 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. 11-RESID-POST-AA
    11. 58841
    Prev
    Next
    INDEX
    Explanations

    Historical figures/history

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on French-language tokens (including accented characters) and related conversation markers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reducer
    -0.07
     至
    -0.07
     drawers
    -0.07
    arket
    -0.07
    [end
    -0.06
    ullet
    -0.06
    login
    -0.06
     Olomou
    -0.06
     Volunteers
    -0.06
     peč
    -0.06
    POSITIVE LOGITS
    TOP
    0.08
    .GetInstance
    0.06
    屏
    0.06
    ivism
    0.06
    .Local
    0.06
     nun
    0.06
     eminent
    0.06
    ply
    0.06
    /Observable
    0.06
    _BIN
    0.06
    Activations Density 0.141%

    No Known Activations