© 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. 57086
    Prev
    Next
    INDEX
    Explanations

    number

    np_max-act · gemini-2.0-flash

    This neuron activates on the numeric token that represents the seconds field in timestamp strings (e.g. the “ss” in “HH:MM:ss”) commonly found in email‐ or log‐style date/time headers.

    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
    _Project
    -0.07
     fichier
    -0.06
    outfile
    -0.06
     Penny
    -0.06
     penny
    -0.06
     dicho
    -0.06
     Ow
    -0.06
    survey
    -0.06
     breakpoint
    -0.06
     Assault
    -0.06
    POSITIVE LOGITS
    plays
    0.07
    etically
    0.06
    .NaN
    0.06
     ERA
    0.06
    uellen
    0.06
     brains
    0.06
    .Cmd
    0.06
     пн
    0.06
    .StartPosition
    0.06
    _SC
    0.06
    Activations Density 0.003%

    No Known Activations