© 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. 125004
    Prev
    Next
    INDEX
    Explanations

    follow

    np_max-act · gemini-2.0-flash

    The neuron activates on the stock introductory phrase “Here is an example of how to …” that launches a descriptive code‐example answer.

    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
    าท
    -0.07
     Anchor
    -0.06
     blobs
    -0.06
     excit
    -0.06
    ี,
    -0.06
    589
    -0.06
    parentNode
    -0.06
     몇
    -0.06
    ерв
    -0.06
     rift
    -0.06
    POSITIVE LOGITS
    _Meta
    0.06
    _purchase
    0.06
    .op
    0.06
     Moroccan
    0.06
     flea
    0.06
     Francesco
    0.06
     CK
    0.06
     pledged
    0.06
    bohydr
    0.06
     Physician
    0.06
    Activations Density 0.021%

    No Known Activations