© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 73952
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron fires on cron‐style scheduling tokens—i.e. the frequency/time specifiers (hourly, daily, weekly, monthly, etc.) and their associated numeric fields in a crontab.

    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
    >".$
    -0.07
    paste
    -0.07
    descriptor
    -0.06
    ,string
    -0.06
    Objects
    -0.06
     delegation
    -0.06
     Lights
    -0.06
     actively
    -0.06
    hoff
    -0.06
    ResultsController
    -0.06
    POSITIVE LOGITS
    _Delete
    0.07
     CreateTable
    0.07
    VersionUID
    0.06
    º
    0.06
     empleado
    0.06
     dripping
    0.06
    /back
    0.06
     bắc
    0.06
     Čes
    0.06
     Coron
    0.06
    Activations Density 0.000%

    No Known Activations