© 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. 59019
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron responds to auxiliary/linking verbs (“is,” “be,” “will,” etc.), especially where they signal passive‐voice constructions.

    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
    ATT
    -0.08
     Bol
    -0.06
    awaii
    -0.06
    -pressure
    -0.06
     Charts
    -0.06
     fab
    -0.06
    occupied
    -0.06
    писок
    -0.06
     defiance
    -0.06
    ATTERY
    -0.06
    POSITIVE LOGITS
     SUBSTITUTE
    0.07
    -spacing
    0.07
    //----------------------------------------------------------------------------↵
    0.07
     çünkü
    0.06
    .Include
    0.06
    DidChange
    0.06
     않는
    0.06
    ProducesResponseType
    0.06
     Detail
    0.06
     evrop
    0.06
    Activations Density 0.152%

    No Known Activations