© 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. 45125
    Prev
    Next
    INDEX
    Explanations

    Week

    np_max-act · gemini-2.0-flash

    This neuron fires on occurrences of “Week” or “week(s)” used as a heading or time marker.

    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
    atar
    -0.07
     cosy
    -0.07
    _failed
    -0.07
    resultado
    -0.07
    Destroy
    -0.07
    _enter
    -0.07
     Surre
    -0.07
    atr
    -0.07
    ared
    -0.07
    isor
    -0.07
    POSITIVE LOGITS
     Week
    0.15
     WEEK
    0.13
    Week
    0.13
     week
    0.13
    week
    0.12
     weeks
    0.11
     Weeks
    0.11
     weekly
    0.11
     Westbrook
    0.09
    Weekly
    0.09
    Activations Density 0.030%

    No Known Activations