© 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. 25270
    Prev
    Next
    INDEX
    Explanations

    providing assistance or asking questions

    np_max-act · gemini-2.0-flash

    The neuron activates on the assistant’s polite clarification/offering-help language (e.g. “I,” “can,” “help,” “provide,” “please”) indicating requests for more context or offers of assistance.

    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
     women
    -0.06
    在线观看
    -0.06
     navíc
    -0.06
     домашних
    -0.06
    dream
    -0.06
     immediate
    -0.06
    ########################################################################
    -0.06
    ばかり
    -0.06
    oscope
    -0.06
     Ön
    -0.06
    POSITIVE LOGITS
    IFn
    0.07
     pulse
    0.06
     fluct
    0.06
    Rnd
    0.06
    Success
    0.06
     Fail
    0.06
    ่าเป
    0.06
     quizzes
    0.06
     Into
    0.06
    \/\/
    0.06
    Activations Density 0.034%

    No Known Activations