© 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. 29487
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens involved in giving numeric measurements—dimensions, sizes, quantities, and units.

    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
    _am
    -0.07
    .github
    -0.06
    asset
    -0.06
    apixel
    -0.06
    FM
    -0.06
    σσ
    -0.06
    rophe
    -0.06
    еред
    -0.06
    났
    -0.06
     BuzzFeed
    -0.06
    POSITIVE LOGITS
     experimental
    0.06
     usleep
    0.06
     RaisedButton
    0.06
    ¯
    0.06
    ıldı
    0.06
    ůže
    0.06
     TERMIN
    0.06
     mulheres
    0.05
    .Hour
    0.05
     succeed
    0.05
    Activations Density 0.012%

    No Known Activations