© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 90717
    Prev
    Next
    INDEX
    Explanations

    round

    np_max-act · gemini-2.0-flash

    information related to football tournaments and teams.

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

    The neuron detects names of competition stages or rounds (e.g. “Preliminary,” “Group,” “Final,” “Qualifying,” “Semifinals,” etc.) in sports/tournament texts.

    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
     brown
    -0.07
     Brown
    -0.07
    Brown
    -0.07
    Ber
    -0.07
     Bin
    -0.06
     dome
    -0.06
     Sight
    -0.06
    씀
    -0.06
     Tar
    -0.06
     Mosque
    -0.06
    POSITIVE LOGITS
     gł
    0.07
     постоянно
    0.07
    ensagem
    0.06
    .hand
    0.06
     نه
    0.06
     metaphor
    0.06
    /lab
    0.06
    crypt
    0.06
    (ag
    0.06
    .Files
    0.06
    Activations Density 0.009%

    No Known Activations