© 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. 89641
    Prev
    Next
    INDEX
    Explanations

    Programming/code

    np_max-act · gemini-2.0-flash

    This neuron detects special structural header markers (e.g. the <|start_header_id|> and related metadata tokens) rather than regular text content.

    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
    _RSP
    -0.07
    argc
    -0.07
    	handler
    -0.07
     نيز
    -0.07
    -mediated
    -0.06
    _pal
    -0.06
    ACHER
    -0.06
    zoom
    -0.06
    يرة
    -0.06
     dividend
    -0.06
    POSITIVE LOGITS
    than
    0.07
    built
    0.07
     External
    0.07
     fill
    0.06
    Full
    0.06
    utable
    0.06
    undles
    0.06
    cter
    0.06
    —even
    0.06
     PRESS
    0.06
    Activations Density 0.556%

    No Known Activations