© 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. 41426
    Prev
    Next
    INDEX
    Explanations

    failure

    np_max-act · gemini-2.0-flash

    This neuron activates on words conveying negative or uncertain judgments in responses (e.g. “irrelevant,” “can’t [decide],” “not recommended”).

    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
    яг
    -0.07
     sed
    -0.06
    :ｉ
    -0.06
     quant
    -0.06
     LoginComponent
    -0.06
    .*?)
    -0.06
     never
    -0.06
     vv
    -0.06
    겠습니다
    -0.06
     users
    -0.06
    POSITIVE LOGITS
     đến
    0.06
    .subscriptions
    0.06
    Partial
    0.06
     Avust
    0.06
    shed
    0.06
     Amy
    0.06
     sill
    0.06
    nock
    0.06
    urally
    0.06
     Northern
    0.06
    Activations Density 0.012%

    No Known Activations