© 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. 102297
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    The neuron fires on the little parenthesized numerals used to mark subsections (e.g. “(1)”, “(3)”) in legal‐code style text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    legal terminology and references related to court cases.

    oai_token-act-pair · gpt-4o-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
     apps
    -0.07
     borrowed
    -0.07
     valid
    -0.07
     explains
    -0.07
     tells
    -0.07
     LOC
    -0.07
     says
    -0.07
     kịp
    -0.06
     barn
    -0.06
     sims
    -0.06
    POSITIVE LOGITS
    rophe
    0.07
    減
    0.06
     разв
    0.06
     persön
    0.06
    еку
    0.06
    कन
    0.06
    行動
    0.06
    βέρ
    0.06
    横
    0.06
     νέ
    0.06
    Activations Density 0.004%

    No Known Activations