© 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. 125214
    Prev
    Next
    INDEX
    Explanations

    else, { (code)

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of an `eq?` comparison testing the first element of a Scheme/Lisp expression (i.e. `(car exp)`) against a quoted symbol.

    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
    ใกล
    -0.08
     terminology
    -0.08
    ши
    -0.07
     группы
    -0.06
    -flow
    -0.06
     initial
    -0.06
    δά
    -0.06
    (binding
    -0.06
    urpose
    -0.06
     averages
    -0.06
    POSITIVE LOGITS
     PROF
    0.07
     Les
    0.06
     захворювання
    0.06
    ^K
    0.06
     skirm
    0.06
     Dunn
    0.06
     INCIDENT
    0.06
     LES
    0.06
    btc
    0.06
     JAN
    0.06
    Activations Density 0.016%

    No Known Activations