© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 38348
    Prev
    Next
    INDEX
    Explanations

    Comma

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on the standalone numeric day (the “8,” “12,” “4,” etc.) in the date headers of the posts—that is, it detects the day-of-month numbers in the document’s date lines.

    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
    assium
    -0.07
    /temp
    -0.06
    laş
    -0.06
     SPR
    -0.06
    -field
    -0.06
    aras
    -0.06
    ποιη
    -0.06
    APPER
    -0.06
     ORDER
    -0.06
    982
    -0.06
    POSITIVE LOGITS
    .randn
    0.06
    .extra
    0.06
     mise
    0.06
     technically
    0.06
     глаз
    0.06
    .Metadata
    0.06
     mechanic
    0.06
    $MESS
    0.06
     /*!<
    0.06
    ges
    0.06
    Activations Density 0.001%

    No Known Activations