© 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. 58237
    Prev
    Next
    INDEX
    Explanations

    exception

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of “exception” and “handling,” i.e. text discussing exception handling terminology.

    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
     przed
    -0.08
    ,sum
    -0.07
    @RequestMapping
    -0.07
     топ
    -0.06
    Functional
    -0.06
    Προ
    -0.06
     ziy
    -0.06
    Jamie
    -0.06
     Sev
    -0.06
     residuals
    -0.06
    POSITIVE LOGITS
     BC
    0.07
     Baghdad
    0.07
     C
    0.06
     hes
    0.06
    .notification
    0.06
    sender
    0.06
    ulação
    0.06
    riba
    0.06
     PCI
    0.06
     GLenum
    0.06
    Activations Density 0.011%

    No Known Activations