© 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. 91146
    Prev
    Next
    INDEX
    Explanations

    occus

    np_max-act · gemini-2.0-flash

    This neuron specializes in picking out scientific and biomedical entity names—such as Latin species names, disease or condition names, and specialized assay or technique terms—in research‐style text.

    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
     PY
    -0.06
    ),$
    -0.06
    pas
    -0.06
     buys
    -0.06
     go
    -0.06
     nominations
    -0.06
     бер
    -0.06
     вост
    -0.06
     restoration
    -0.06
     reduces
    -0.06
    POSITIVE LOGITS
    -Mobile
    0.07
    andom
    0.07
    /cloud
    0.07
     IonicPage
    0.07
    ountains
    0.07
    -boot
    0.06
    .params
    0.06
    -color
    0.06
    �始
    0.06
    点击
    0.06
    Activations Density 0.240%

    No Known Activations