© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 43318
    Prev
    Next
    INDEX
    Explanations

    sports leagues

    np_max-act · gemini-2.0-flash

    The neuron identifies mentions of a football league’s organizational hierarchy—terms referring to league systems, tiers/levels, and their formal names.

    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
    jwt
    -0.07
    Row
    -0.07
    <Token
    -0.07
    Jwt
    -0.06
     filmmakers
    -0.06
    	pw
    -0.06
     Skip
    -0.06
    	id
    -0.06
     colormap
    -0.06
    OfWeek
    -0.06
    POSITIVE LOGITS
    唯
    0.07
     rested
    0.07
     vuel
    0.06
    ／
    0.06
    \core
    0.06
     fed
    0.06
     ск
    0.06
    τύ
    0.06
    /i
    0.06
    ắc
    0.06
    Activations Density 0.030%

    No Known Activations