Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 91
    Prev
    Next
    INDEX
    Explanations

    able

    np_max-act · gemini-2.0-flash

    This neuron detects the special header‐delimiter tokens (e.g. `<|start_header_id|>` and `<|end_header_id|>`) that mark the conversation metadata sections.

    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
     нового
    -0.07
     discoveries
    -0.07
     tastes
    -0.06
     Authors
    -0.06
     Herc
    -0.06
    _sample
    -0.06
     Beef
    -0.06
    .Guna
    -0.06
    riors
    -0.06
    _constant
    -0.06
    POSITIVE LOGITS
    '")↵
    0.07
     lex
    0.06
     배열
    0.06
    (){}↵
    0.06
    ு
    0.06
     exped
    0.06
     初始化
    0.06
    	cs
    0.06
     ceasefire
    0.06
    登
    0.06
    Activations Density 0.049%

    No Known Activations