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. 90390
    Prev
    Next
    INDEX
    Explanations

    24-hour races

    np_max-act · gemini-2.0-flash

    technical details and achievements related to motorsports, particularly in car racing.

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

    This neuron detects mentions of endurance racing events specified as “<number> Hours” (e.g., “24 Hours of Daytona,” “12 Hours of Sebring,” “24 Hours of Le Mans”).

    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
     Cold
    -0.07
    aterangepicker
    -0.06
     кан
    -0.06
    .addTarget
    -0.06
    飯
    -0.06
    interfaces
    -0.06
    (choices
    -0.06
    -close
    -0.06
    (nullable
    -0.06
    dice
    -0.06
    POSITIVE LOGITS
    -rich
    0.08
    berry
    0.06
    σα
    0.06
     Crist
    0.06
     smelling
    0.06
    una
    0.06
    _click
    0.06
    AMI
    0.06
    Truthy
    0.06
    urations
    0.06
    Activations Density 0.006%

    No Known Activations