© 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. 44662
    Prev
    Next
    INDEX
    Explanations

    up/off endings

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “cleanup” (and closely related decontamination/cleanup terms).

    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
     element
    -0.07
     elect
    -0.07
     역사
    -0.06
     directions
    -0.06
    _categories
    -0.06
    _measure
    -0.06
     engraved
    -0.06
    元素
    -0.06
    >[↵
    -0.06
    Serializable
    -0.06
    POSITIVE LOGITS
     Cleanup
    0.09
    -up
    0.09
    up
    0.09
     Lawson
    0.09
    ups
    0.08
    ko
    0.08
    .O
    0.08
    KO
    0.08
     pickup
    0.08
     setup
    0.08
    Activations Density 0.049%

    No Known Activations