© 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. 44783
    Prev
    Next
    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash

    This neuron responds to words and phrases that discuss wrapping up a narrative—conclusions, endings, resolutions, and tying up loose ends.

    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
     ".";↵
    -0.07
     Toe
    -0.07
    ,get
    -0.07
    _read
    -0.07
     "";
    -0.07
     cut
    -0.07
    (Paint
    -0.07
     طراحی
    -0.07
    =edge
    -0.07
    Crop
    -0.06
    POSITIVE LOGITS
     peculiar
    0.06
     dla
    0.06
     recovered
    0.06
     라
    0.06
    мотря
    0.05
    CONDITION
    0.05
    _NEED
    0.05
     Exiting
    0.05
    (Duration
    0.05
     MOZ
    0.05
    Activations Density 0.033%

    No Known Activations