© 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. 126007
    Prev
    Next
    INDEX
    Explanations

    Code with numerical logic

    np_max-act · gemini-2.0-flash

    This neuron detects tokens belonging to the plural‐forms expression (the “n%10…n%100” conditional formula) in translation files.

    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
    heads
    -0.07
    क
    -0.07
     pixels
    -0.06
     Hurt
    -0.06
    .ToLower
    -0.06
     Encode
    -0.06
     опред
    -0.06
     협
    -0.06
     Rogers
    -0.06
     _↵↵
    -0.06
    POSITIVE LOGITS
    rief
    0.07
    -spec
    0.06
     çeşitli
    0.06
    (Settings
    0.06
    -seeking
    0.06
    рогра
    0.06
    /releases
    0.06
    (PDO
    0.06
    _sold
    0.06
    patients
    0.06
    Activations Density 0.003%

    No Known Activations