© 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. 39032
    Prev
    Next
    INDEX
    Explanations

    Monthly

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of time-length phrases (e.g. “3 months,” “7-day,” “one week”) indicating the duration of a plan or schedule.

    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
     chiều
    -0.07
    Daemon
    -0.07
     мали
    -0.07
    _connect
    -0.06
     swap
    -0.06
     speedy
    -0.06
    /video
    -0.06
     boundary
    -0.06
    mart
    -0.06
    cxx
    -0.06
    POSITIVE LOGITS
    HasMaxLength
    0.07
    orrh
    0.07
     exempt
    0.07
    -lasting
    0.06
     Quốc
    0.06
     meisten
    0.06
    '},↵
    0.06
     LUA
    0.06
     Veranst
    0.06
    ruba
    0.06
    Activations Density 0.030%

    No Known Activations