© 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. 126810
    Prev
    Next
    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash

    It flags the assistant’s stock clarification prompt—phrases like “Do you have any specific questions…?” asking the user for more details.

    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
    807
    -0.07
    (['/
    -0.06
    Numbers
    -0.06
    ,next
    -0.06
    atak
    -0.06
    ̣
    -0.06
     leftist
    -0.06
    edef
    -0.06
     chiefly
    -0.06
     REUTERS
    -0.06
    POSITIVE LOGITS
     grupos
    0.07
     connect
    0.06
     Ne
    0.06
    among
    0.06
    invert
    0.06
     Spr
    0.06
    keit
    0.06
     düz
    0.06
     darkness
    0.06
     두
    0.06
    Activations Density 0.076%

    No Known Activations