© 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 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. 38996
    Prev
    Next
    INDEX
    Explanations

    his

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on tokens that mark or form section headings (e.g. header‐ID markers and section titles) in the text.

    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
    abd
    -0.06
     shepherd
    -0.06
    _CHO
    -0.06
     languages
    -0.06
     Comparative
    -0.06
    uxe
    -0.06
     Counties
    -0.06
    ==========
    -0.06
    徒
    -0.06
     nextProps
    -0.06
    POSITIVE LOGITS
    _mono
    0.06
    licht
    0.06
    promotion
    0.06
     vai
    0.06
    RESH
    0.06
     Gaw
    0.06
     Ich
    0.06
     uç
    0.06
    /debug
    0.06
     intellectuals
    0.06
    Activations Density 0.147%

    No Known Activations