© 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. 39127
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by floating-point numeric literals (decimal numbers) in the code.

    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
    уст
    -0.09
     :\
    -0.07
    职
    -0.07
    /F
    -0.07
    사를
    -0.06
    递
    -0.06
     thuốc
    -0.06
    .inv
    -0.06
     Ob
    -0.06
    (av
    -0.06
    POSITIVE LOGITS
    (QtCore
    0.07
     sett
    0.06
     awaiting
    0.06
     downtown
    0.06
     ----------------------------------------------------------------------↵
    0.06
     dao
    0.06
     adamant
    0.06
    ApiOperation
    0.06
     imminent
    0.06
     Stokes
    0.06
    Activations Density 0.011%

    No Known Activations