© 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. 128297
    Prev
    Next
    INDEX
    Explanations

    Negation/Refusal

    np_max-act · gemini-2.0-flash

    This neuron detects words in refusal statements (e.g., “refuse to answer”) indicating a refusal or inability to comply.

    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
     процесса
    -0.07
    (chan
    -0.06
     invaded
    -0.06
    대학교
    -0.06
     Xia
    -0.06
    _rule
    -0.06
     آلات
    -0.06
     MOR
    -0.06
    談
    -0.06
    tains
    -0.06
    POSITIVE LOGITS
    	super
    0.07
    abbr
    0.07
    .LayoutInflater
    0.07
     제품
    0.07
     урож
    0.07
    -password
    0.06
     unrest
    0.06
    Youtube
    0.06
    Strict
    0.06
    ','%
    0.06
    Activations Density 0.000%

    No Known Activations