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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 68576
    Prev
    Next
    INDEX
    Explanations

    a or 's

    np_max-act · gemini-2.0-flash

    The neuron detects language around refusal or rejection of requests (e.g. “reject a question,” “declined,” “refuse”).

    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
     Kelley
    -0.07
     stated
    -0.06
     Kale
    -0.06
     migrants
    -0.06
    pawn
    -0.06
    encv
    -0.06
     bilg
    -0.06
    _elt
    -0.06
     posting
    -0.06
     вост
    -0.06
    POSITIVE LOGITS
    IconButton
    0.07
    ث
    0.07
     Tư
    0.06
    пи
    0.06
     بودن
    0.06
    StateMachine
    0.06
    нив
    0.06
    _MATERIAL
    0.06
    Disclaimer
    0.06
    her
    0.06
    Activations Density 0.001%

    No Known Activations