© 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 EvalsExportsinterp-engineNEWAPI 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. 58852
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on temporal markers—dates, durations, and time-related words (e.g. months, days, “from,” “began,” numeric dates).

    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
    ience
    -0.07
     дома
    -0.06
    uš
    -0.06
    (Device
    -0.06
    ndl
    -0.06
    />";↵
    -0.06
    نجليزية
    -0.06
    赖
    -0.06
    rams
    -0.06
     Siemens
    -0.06
    POSITIVE LOGITS
     brutally
    0.07
    Concurrency
    0.07
     признач
    0.07
     ern
    0.07
    <tbody
    0.06
     چگونه
    0.06
    .gr
    0.06
     mMap
    0.06
     acct
    0.06
     бактер
    0.06
    Activations Density 0.024%

    No Known Activations