© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89756
    Prev
    Next
    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash

    The neuron detects tokens in the assistant’s polite refusal or denial responses (e.g., “I’m sorry, but I cannot fulfill this request”).

    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
     restore
    -0.07
     Runtime
    -0.07
    oproject
    -0.06
    랍
    -0.06
    	filter
    -0.06
     extinction
    -0.06
     AZ
    -0.06
     warming
    -0.06
     bypass
    -0.06
     richest
    -0.06
    POSITIVE LOGITS
    多い
    0.07
    ifications
    0.07
    تبه
    0.06
    .XRTableCell
    0.06
    olutions
    0.06
     PED
    0.06
     IE
    0.06
    iii
    0.06
    ================================================================
    0.06
    auté
    0.06
    Activations Density 0.005%

    No Known Activations