© 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
    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. 89332
    Prev
    Next
    INDEX
    Explanations

    Story beginnings

    np_max-act · gemini-2.0-flash

    This neuron detects special structural/control tokens (e.g. header-ID markers like “<|start_header_id|>”) rather than regular content words.

    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
     Сан
    -0.07
    .Download
    -0.06
    (test
    -0.06
     rho
    -0.06
     battled
    -0.06
     Boise
    -0.06
     Escape
    -0.06
     Gar
    -0.06
    يت
    -0.06
    EST
    -0.06
    POSITIVE LOGITS
    YPRE
    0.07
    =sub
    0.07
    yyvsp
    0.07
    にか
    0.06
     stm
    0.06
     (!((
    0.06
     가
    0.06
     injections
    0.06
    /utility
    0.06
    ，也
    0.06
    Activations Density 0.153%

    No Known Activations