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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58879
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron detects in-text stage directions or action descriptions, especially those enclosed in asterisks.

    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
     compr
    -0.07
    rogate
    -0.07
     противоп
    -0.06
     water
    -0.06
     vest
    -0.06
     WATER
    -0.06
     Water
    -0.06
    Sleep
    -0.06
     POV
    -0.06
     spectator
    -0.06
    POSITIVE LOGITS
    _AspNet
    0.07
    ━━━━━━━━
    0.06
     неболь
    0.06
    (fetch
    0.06
     Через
    0.06
    '=>
    0.06
     depois
    0.06
     वजह
    0.06
    );}↵↵
    0.06
    .exc
    0.06
    Activations Density 0.036%

    No Known Activations