© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110106
    Prev
    Next
    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash

    This neuron fires on prominent headline or title–style tokens, especially capitalized names, entities, and key banner words.

    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
    나라
    -0.06
    release
    -0.06
     Abr
    -0.06
     registr
    -0.06
    .Search
    -0.06
    qb
    -0.05
    /stats
    -0.05
    aning
    -0.05
     apis
    -0.05
     remin
    -0.05
    POSITIVE LOGITS
     dozens
    0.07
    egl
    0.07
    -Isl
    0.06
     initWithTitle
    0.06
    Backdrop
    0.06
    {l
    0.06
     Eigen
    0.06
    ,function
    0.06
    llib
    0.06
    Colon
    0.06
    Activations Density 0.090%

    No Known Activations