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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12502
    Prev
    Next
    INDEX
    Explanations

    7

    np_max-act · gemini-2.0-flash

    This neuron primarily fires on digit‐only tokens, i.e. it detects numbers (multi-digit numerical strings) in the text.

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

    details related to aviation incidents and airline operations.

    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
     Await
    -0.06
     Lud
    -0.06
     distinctive
    -0.06
     SERVER
    -0.06
     Bened
    -0.06
    上が
    -0.06
    dfs
    -0.06
     ей
    -0.06
     leur
    -0.06
    -income
    -0.06
    POSITIVE LOGITS
    ubi
    0.06
     очист
    0.06
    			     
    0.06
     Jub
    0.06
    (hWnd
    0.06
    se
    0.06
     dollars
    0.06
    งเป
    0.06
    .getStatusCode
    0.06
     spielen
    0.06
    Activations Density 0.000%

    No Known Activations