© 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. 6322
    Prev
    Next
    INDEX
    Explanations

    oplast

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of corneal transplantation procedures (e.g. “keratoplasty”).

    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
    _SIG
    -0.07
    .responses
    -0.07
    (bucket
    -0.07
    ώς
    -0.06
    _origin
    -0.06
    [Math
    -0.06
    、小
    -0.06
    (contract
    -0.06
     Finance
    -0.06
     resultSet
    -0.06
    POSITIVE LOGITS
     fitted
    0.07
     comunic
    0.06
    .player
    0.06
     Slug
    0.06
     court
    0.06
    _sa
    0.06
    delta
    0.06
     repe
    0.06
     국
    0.06
    âl
    0.06
    Activations Density 0.001%

    No Known Activations