Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 85844
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash

    The neuron activates on molecular biology–style protein or gene identifiers (e.g. capitalized alphanumeric names often ending with “p”).

    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
    .toolStrip
    -0.07
    elo
    -0.07
    %f
    -0.07
     آش
    -0.07
    ctest
    -0.06
    Html
    -0.06
     crossword
    -0.06
    .Visible
    -0.06
    issant
    -0.06
    Maria
    -0.06
    POSITIVE LOGITS
    .STATE
    0.06
    ΑΤ
    0.06
     {}
    ↵
    0.06
    _he
    0.06
    ﻠ
    0.06
     зал
    0.06
     getters
    0.06
    \:
    0.06
    ../../../
    0.06
     tenure
    0.06
    Activations Density 0.007%

    No Known Activations