© 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 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. 56732
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    This neuron lights up on subordinating conjunctions and clause-introducing words (e.g. “when,” “if,” “even,” commas signaling sentence breaks) that mark conditional or dependent clauses.

    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
     Barbie
    -0.06
    works
    -0.06
    mek
    -0.06
    viewer
    -0.06
    丈
    -0.06
     hostage
    -0.06
    atsu
    -0.06
     astronauts
    -0.06
    _len
    -0.06
    -0.06
    POSITIVE LOGITS
    .getenv
    0.07
    ('');↵↵
    0.07
    erta
    0.06
     //~
    0.06
     дальней
    0.06
    EmptyEntries
    0.06
    ال
    0.06
    *',
    0.06
    .TextImageRelation
    0.06
     Fol
    0.06
    Activations Density 0.160%

    No Known Activations