© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59332
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron is activated by common discourse/connective words (e.g. “and,” “which,” “such,” “includes,” “when”) that serve to link clauses or introduce steps.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     affection
    -0.08
     included
    -0.06
     on
    -0.06
    699
    -0.06
     collector
    -0.06
     diseñ
    -0.06
     определен
    -0.06
     detects
    -0.06
     pellet
    -0.06
     Process
    -0.06
    POSITIVE LOGITS
    ardır
    0.07
    ,end
    0.06
     Jays
    0.06
     Reno
    0.06
    ,A
    0.06
     شود
    0.06
     Я
    0.06
    .AddComponent
    0.06
    byterian
    0.06
    asic
    0.06
    Activations Density 1.315%

    No Known Activations