© 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. 7-RESID-POST-AA
    11. 31117
    Prev
    Next
    INDEX
    Explanations

    assistant

    np_max-act · gemini-2.0-flash

    mentions of the “Assistant” role label or references to the AI assistant in chat/transcript-style formatting.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LG
    -0.08
    地域
    -0.07
     geopolitical
    -0.07
     gin
    -0.06
     Feng
    -0.06
     photon
    -0.06
     KDE
    -0.06
     liqu
    -0.06
     انقل
    -0.06
     energie
    -0.06
    POSITIVE LOGITS
     Assistant
    0.13
     assistant
    0.11
    Assistant
    0.10
    ificant
    0.08
    맞
    0.07
     clerk
    0.07
    アン
    0.07
    sters
    0.07
     suitability
    0.07
     assistants
    0.06
    Activations Density 0.028%

    No Known Activations