© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41394
    Prev
    Next
    INDEX
    Explanations

    haven

    np_max-act · gemini-2.0-flash

    This neuron detects the special tokens that mark the end of an exchange’s header (i.e. the “<|end_header_id|>” boundary in the conversation data).

    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
    .tagName
    -0.07
     Angle
    -0.07
    (Y
    -0.07
    ствен
    -0.07
    ,unsigned
    -0.06
     подс
    -0.06
     thiểu
    -0.06
    úb
    -0.06
     JsonRequest
    -0.06
    够
    -0.06
    POSITIVE LOGITS
     Wolff
    0.06
     dissatisfaction
    0.06
    新闻
    0.06
     tongue
    0.06
     cannons
    0.06
     dispatch
    0.06
    "{
    0.06
    	dispatch
    0.06
    ::*;↵
    0.06
     Malays
    0.06
    Activations Density 0.015%

    No Known Activations