Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 8179
    Prev
    Next
    INDEX
    Explanations

    sports leagues

    np_max-act · gemini-2.0-flash

    information related to sports events and athletes.

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

    This neuron responds to mentions of sports leagues, conferences, or divisions (e.g., “Premiership Rugby,” “Northeast Conference,” “Sunshine State Conference”).

    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
    Dto
    -0.07
    .ip
    -0.06
    (pkt
    -0.06
     canned
    -0.06
    hil
    -0.06
     Interest
    -0.06
    /check
    -0.06
    _five
    -0.06
    [js
    -0.06
     bw
    -0.05
    POSITIVE LOGITS
     enrich
    0.08
     irritation
    0.07
     Mou
    0.07
     редак
    0.07
    vas
    0.07
     फ
    0.07
     ASM
    0.07
     SCH
    0.06
     घटन
    0.06
    见
    0.06
    Activations Density 0.166%

    No Known Activations