© 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. 73958
    Prev
    Next
    INDEX
    Explanations

    here

    np_max-act · gemini-2.0-flash

    graphic and explicit sexual interactions involving taboo themes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects brief self-introductions or meta-narrative cues—instances where the speaker names themselves and says “here,” “I am,” or similar.

    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
    .Function
    -0.06
     pazar
    -0.06
     pelos
    -0.06
     snowy
    -0.06
    .ExecuteNonQuery
    -0.06
    Support
    -0.06
     syst
    -0.06
    .Zip
    -0.06
     тисяч
    -0.06
    $options
    -0.06
    POSITIVE LOGITS
    (mouse
    0.08
    erture
    0.07
     Interstate
    0.06
    ху
    0.06
    482
    0.06
    igraphy
    0.06
    IGATION
    0.06
    uppy
    0.06
     shortcuts
    0.06
     arbe
    0.06
    Activations Density 0.003%

    No Known Activations