© 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
    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. 90768
    Prev
    Next
    INDEX
    Explanations

    -American

    np_max-act · gemini-2.0-flash

    information about American football players, their careers, and statistics.

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

    The main thing this neuron does is detect mentions of athletic honors or recruit rankings (e.g. star-recruit designations, All-Conference/American awards).

    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
    })();
    -0.06
     Collider
    -0.06
    WF
    -0.06
    HEEL
    -0.06
     ürün
    -0.06
    .Detail
    -0.06
     UX
    -0.06
     Tunis
    -0.05
     sonucu
    -0.05
             ↵
    -0.05
    POSITIVE LOGITS
    ету
    0.07
     modification
    0.07
     dau
    0.07
     Alice
    0.07
    [d
    0.06
    Sampling
    0.06
     ح
    0.06
     accom
    0.06
     tissue
    0.06
    ulares
    0.06
    Activations Density 0.003%

    No Known Activations