© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59235
    Prev
    Next
    INDEX
    Explanations

    technology

    np_max-act · gemini-2.0-flash

    technical descriptions related to electronic devices and their components.

    oai_token-act-pair · gpt-4o-mini
    Triggered by @xinyanhu8

    The neuron activates on technical process nouns ending in “-ization” (e.g. “miniaturization”) and related engineering jargon.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     Shaman
    -0.06
    neys
    -0.06
    .baseUrl
    -0.06
     Heller
    -0.06
    athers
    -0.06
    ۲۳
    -0.06
    always
    -0.06
    roys
    -0.06
     phía
    -0.06
    ecake
    -0.06
    POSITIVE LOGITS
    foregroundColor
    0.07
    ,/
    0.07
     *****
    0.06
    樓
    0.06
    licken
    0.06
    iterator
    0.06
    —
    0.06
    _producto
    0.06
     бел
    0.06
    ------------------------------
    0.06
    Activations Density 0.068%

    No Known Activations