© 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. 126998
    Prev
    Next
    INDEX
    Explanations

    URLs and random characters

    np_max-act · gemini-2.0-flash

    The neuron is primarily triggered by numeric tokens, i.e. digits and numbers embedded in text (such as timestamps, IDs, dimensions, and other digit sequences).

    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
     thieves
    -0.07
     NATIONAL
    -0.07
     Average
    -0.06
    Provides
    -0.06
    ING
    -0.06
    (join
    -0.06
     Fern
    -0.06
    <Test
    -0.06
     Finch
    -0.06
     vaguely
    -0.06
    POSITIVE LOGITS
     banc
    0.06
    wrapped
    0.06
     쪽지
    0.06
     sonraki
    0.06
    idebar
    0.06
    CW
    0.06
    apollo
    0.06
    pekt
    0.06
    .co
    0.06
    ています
    0.06
    Activations Density 0.035%

    No Known Activations