© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13573
    Prev
    Next
    INDEX
    Explanations

    Coding questions and answers

    np_max-act · gemini-2.0-flash

    This neuron fires on the word "Write," detecting the imperative that begins a user’s coding request.

    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
     toes
    -0.07
    坚
    -0.07
    Vals
    -0.07
     retorna
    -0.06
    dfd
    -0.06
     Besch
    -0.06
     Dar
    -0.06
    Storyboard
    -0.06
     svou
    -0.06
     همیشه
    -0.06
    POSITIVE LOGITS
     industrial
    0.06
    网刊
    0.06
     trục
    0.06
    _cp
    0.06
    \db
    0.06
    />.↵↵
    0.06
     xx
    0.06
    osoph
    0.06
    unistd
    0.06
     rais
    0.06
    Activations Density 0.040%

    No Known Activations