© 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 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. 11-RESID-POST-AA
    11. 56619
    Prev
    Next
    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash

    This neuron responds most strongly to longer, multi-syllable technical terms (especially complex medical or scientific jargon).

    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
    _<?
    -0.06
    __[
    -0.06
    ДА
    -0.06
    nodes
    -0.06
     Reads
    -0.06
    <d
    -0.06
    ้ว
    -0.06
    xffffff
    -0.06
    (points
    -0.06
     cols
    -0.06
    POSITIVE LOGITS
    減
    0.07
    eso
    0.06
     questioned
    0.06
     amended
    0.06
     exhibition
    0.06
    Digit
    0.06
    ัดการ
    0.06
    _FE
    0.06
     researched
    0.06
     streamed
    0.06
    Activations Density 0.165%

    No Known Activations