© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55818
    Prev
    Next
    INDEX
    Explanations

    Console

    np_max-act · gemini-2.0-flash

    This neuron detects special role-tag and header-boundary tokens that mark the start or end of the assistant’s response (e.g. “<|end_header_id|>”, the “assistant” tag, and similar metadata markers).

    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
     있는데
    -0.07
    wards
    -0.06
    ẽ
    -0.06
    tile
    -0.06
    ดย
    -0.06
     BUTTON
    -0.06
    iable
    -0.06
     自动生成
    -0.06
     ISPs
    -0.06
    े,
    -0.06
    POSITIVE LOGITS
    .Symbol
    0.07
     appearance
    0.07
     Worldwide
    0.07
    capitalize
    0.06
    pectral
    0.06
     Juice
    0.06
    XE
    0.06
    원을
    0.06
    ूबर
    0.06
    relude
    0.06
    Activations Density 0.008%

    No Known Activations