© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 65200
    Prev
    Next
    INDEX
    Explanations

    Fighting outcomes

    np_max-act · gemini-2.0-flash

    This neuron spotlights mentions of fight rounds and decision outcomes (e.g., numeric “round” references and verdict words like “decision”).

    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
     setPassword
    -0.06
     butto
    -0.06
     وهي
    -0.06
    .MixedReality
    -0.06
     дости
    -0.06
    ている
    -0.06
     آتش
    -0.06
     createStackNavigator
    -0.06
     Ziel
    -0.06
    ipline
    -0.06
    POSITIVE LOGITS
    mise
    0.07
     taille
    0.07
     ventured
    0.06
     ana
    0.06
     пла
    0.06
     graf
    0.06
     juice
    0.06
     gets
    0.06
    chyb
    0.06
    icides
    0.06
    Activations Density 0.003%

    No Known Activations