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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 39115
    Prev
    Next
    INDEX
    Explanations

    stop words and "be"

    np_max-act · gemini-2.0-flash

    This neuron responds to the special “header ID” markers (e.g. <|start_header_id|> and its paired tags) that delineate system/user/assistant blocks.

    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
     ftp
    -0.07
     ankle
    -0.06
     fly
    -0.06
     stringify
    -0.06
     спрос
    -0.06
     tact
    -0.06
     Julian
    -0.06
     overlays
    -0.06
     Whitney
    -0.06
     Jaw
    -0.06
    POSITIVE LOGITS
    /load
    0.06
     tehlik
    0.06
     herald
    0.06
    AsString
    0.06
    を行
    0.06
     defenders
    0.06
     세계
    0.06
     mně
    0.06
    .Speed
    0.06
    Editable
    0.06
    Activations Density 0.046%

    No Known Activations