© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 56274
    Prev
    Next
    INDEX
    Explanations

    college sports teams, seasons

    np_max-act · gemini-2.0-flash

    This neuron detects the characteristic opening phrases of Wikipedia-style college (and other) sports team season articles—especially the year-school-team-sport constructs like “1912 Oregon Webfoots football team represented the University…”

    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
    195
    -0.07
     طی
    -0.07
     Communication
    -0.06
     gamble
    -0.06
    194
    -0.06
    tracts
    -0.06
    Rs
    -0.06
     SIMD
    -0.06
    cor
    -0.06
    RR
    -0.05
    POSITIVE LOGITS
    Œ
    0.07
     ability
    0.07
    .Slf
    0.06
    $status
    0.06
     sobě
    0.06
    =ax
    0.06
     حضور
    0.06
    .unsqueeze
    0.06
    Gravity
    0.06
    	Created
    0.06
    Activations Density 0.118%

    No Known Activations