© 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. 12204
    Prev
    Next
    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that specify time-zone offsets (e.g. “GMT”, “+02:00” parts) in date/time strings.

    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
     checkpoint
    -0.06
    Temperature
    -0.06
     součástí
    -0.06
    _VERIFY
    -0.06
     checkpoints
    -0.06
    ailable
    -0.06
    FileVersion
    -0.06
     assault
    -0.06
     Та
    -0.06
     intimidation
    -0.06
    POSITIVE LOGITS
    iž
    0.08
     commem
    0.07
    药
    0.06
     posters
    0.06
    {-
    0.06
    ılım
    0.06
    (BASE
    0.06
    .examples
    0.06
    marketing
    0.06
     skon
    0.06
    Activations Density 0.002%

    No Known Activations