© 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. 110445
    Prev
    Next
    INDEX
    Explanations

    conversational

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on the special role‐label token that marks the start of the assistant’s response (the `<|start_header_id|>` marker).

    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
    "encoding
    -0.07
     Rav
    -0.07
    -INF
    -0.07
     Hentai
    -0.07
     tabBar
    -0.07
     Rut
    -0.07
    .parents
    -0.06
     osm
    -0.06
     series
    -0.06
     stderr
    -0.06
    POSITIVE LOGITS
     newPath
    0.07
     využí
    0.06
     Colombia
    0.06
     захворю
    0.06
    ourke
    0.06
     Francisco
    0.06
    ína
    0.06
    лі
    0.06
     Martins
    0.06
     přibliž
    0.05
    Activations Density 0.026%

    No Known Activations