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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 92173
    Prev
    Next
    INDEX
    Explanations

    mi

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of PowerShell WMI commands (e.g. Get-WmiObject) and related WMI class invocations.

    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
     mega
    -0.06
     cel
    -0.06
     wirklich
    -0.06
    /desktop
    -0.06
     deposits
    -0.06
     Patron
    -0.06
    AMB
    -0.06
    .mem
    -0.06
     defendants
    -0.06
    Album
    -0.06
    POSITIVE LOGITS
     cài
    0.07
    UTION
    0.07
     transmissions
    0.07
     jmp
    0.06
     pretending
    0.06
    $img
    0.06
     socio
    0.06
     timestep
    0.06
     작업
    0.06
    mouseover
    0.06
    Activations Density 0.002%

    No Known Activations