© 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. 128284
    Prev
    Next
    INDEX
    Explanations

    cricket

    np_max-act · gemini-2.0-flash

    details about sports tournaments, specifically cricket matches.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on references to bowling in cricket, such as mentions of bowlers, their deliveries (e.g. overs, spells), and bowling styles (pace, spin).

    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
     negotiations
    -0.06
    ılığı
    -0.06
    Gtk
    -0.06
     hei
    -0.06
    efa
    -0.06
    、↵
    -0.06
    .Encode
    -0.06
    IEL
    -0.06
    _VARS
    -0.06
    -field
    -0.06
    POSITIVE LOGITS
     доб
    0.07
    empo
    0.06
    śmy
    0.06
     �
    0.06
    NetBar
    0.06
     fulfilled
    0.06
    ア
    0.06
     sức
    0.06
    seen
    0.06
     crumbling
    0.06
    Activations Density 0.004%

    No Known Activations