© 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
    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. 6106
    Prev
    Next
    INDEX
    Explanations

    Racing

    np_max-act · gemini-2.0-flash

    The neuron activates on superlative performance and timing phrases—especially mentions of setting or posting the fastest/best times in racing contexts.

    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
     understandably
    -0.08
    んと
    -0.07
     bushes
    -0.07
     countryside
    -0.07
     döneminde
    -0.06
     düzenli
    -0.06
    ewolf
    -0.06
     Muse
    -0.06
    _off
    -0.06
    σι
    -0.06
    POSITIVE LOGITS
    erialized
    0.07
    RGBO
    0.06
    "}↵↵
    0.06
     ↵        ↵
    0.06
     ambiance
    0.06
     ive
    0.06
     ↵    ↵
    0.06
     enticing
    0.06
     POSSIBILITY
    0.06
     valueType
    0.06
    Activations Density 0.004%

    No Known Activations