© 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. 125080
    Prev
    Next
    INDEX
    Explanations

    water/toy fights, throwing things

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of tomato-throwing or messy fight events (e.g., La Tomatina and similar “fight of the tomatoes” descriptions).

    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
    likes
    -0.07
    /users
    -0.07
     Points
    -0.07
     shadows
    -0.07
     cite
    -0.07
     samo
    -0.07
    439
    -0.06
     avait
    -0.06
     respects
    -0.06
     самостоятельно
    -0.06
    POSITIVE LOGITS
     yaptığ
    0.06
    ังก
    0.06
     adolescente
    0.06
     механи
    0.06
     중요
    0.06
     trí
    0.06
    -vector
    0.06
     เกม
    0.06
    -low
    0.06
     kadın
    0.06
    Activations Density 0.007%

    No Known Activations