© 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. 56865
    Prev
    Next
    INDEX
    Explanations

    m

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting the two‐digit numeric date components (e.g. “01,” “23”) within ISO-style date strings separated by hyphens.

    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
     Death
    -0.07
    کنون
    -0.06
    $objPHPExcel
    -0.06
    .SetParent
    -0.06
     leží
    -0.06
    Xi
    -0.06
     UPS
    -0.06
    .LinearLayout
    -0.06
    .Resolve
    -0.06
     SMA
    -0.06
    POSITIVE LOGITS
     COMMIT
    0.07
    /rc
    0.07
    ointed
    0.06
    .resources
    0.06
     kvinner
    0.06
     publishes
    0.06
    _SOC
    0.06
    .uc
    0.06
     ㅡ
    0.06
     typeof
    0.06
    Activations Density 0.010%

    No Known Activations