© 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. 54006
    Prev
    Next
    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash

    This neuron activates on argument‐placeholder tokens (names enclosed in “<” and “>”) in CLI option/usage strings.

    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
    conciliation
    -0.06
    /front
    -0.06
     آینده
    -0.06
     flotation
    -0.06
     Candle
    -0.06
    इन
    -0.06
    staff
    -0.06
    多少
    -0.06
     scramble
    -0.06
     gem
    -0.06
    POSITIVE LOGITS
     récup
    0.07
    touch
    0.06
     Preview
    0.06
     прох
    0.06
    \Doctrine
    0.06
    inois
    0.06
     подс
    0.06
    .Msg
    0.06
     constr
    0.06
     curly
    0.06
    Activations Density 0.007%

    No Known Activations