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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58252
    Prev
    Next
    INDEX
    Explanations

    Issues and definitions

    np_max-act · gemini-2.0-flash

    The neuron responds to tokens in disclaimers or refusals—phrases stating that something “is not” recognized, appropriate, safe, or allowed.

    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
     discouraged
    -0.06
     سو
    -0.06
    rus
    -0.06
    -wsj
    -0.06
     assault
    -0.06
     evacuation
    -0.06
     presidential
    -0.06
    birth
    -0.06
     بور
    -0.06
    oty
    -0.06
    POSITIVE LOGITS
    /logger
    0.07
     promin
    0.07
    .cn
    0.07
    _Comm
    0.06
     metaph
    0.06
    (buf
    0.06
    _alive
    0.06
    änn
    0.06
    aml
    0.06
     Numero
    0.06
    Activations Density 0.037%

    No Known Activations