© 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. 9298
    Prev
    Next
    INDEX
    Explanations

    football

    np_max-act · gemini-2.0-flash

    This neuron activates on the word “football,” flagging mentions of that sport (e.g. “football competition,” “association football,” etc.).

    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
    Tek
    -0.07
    整个
    -0.06
    eping
    -0.06
    凉
    -0.06
    Bar
    -0.06
    ertain
    -0.06
    LENGTH
    -0.06
    quared
    -0.06
    ILINE
    -0.06
    '}}
    -0.06
    POSITIVE LOGITS
    htmlspecialchars
    0.08
     escal
    0.07
    .writeHead
    0.07
    ์ได
    0.07
     ц
    0.06
    strand
    0.06
    Als
    0.06
     капит
    0.06
    lescope
    0.06
     sr
    0.06
    Activations Density 0.011%

    No Known Activations