© 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. 57597
    Prev
    Next
    INDEX
    Explanations

    wipe

    np_max-act · gemini-2.0-flash

    This neuron activates on imperatives telling you to “wipe down” (i.e., instructions to wipe surfaces).

    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
    618
    -0.08
     prix
    -0.07
     NX
    -0.07
     bones
    -0.07
     teamwork
    -0.07
    σιο
    -0.07
    NavController
    -0.07
    306
    -0.06
     téc
    -0.06
     ostrov
    -0.06
    POSITIVE LOGITS
     wipe
    0.11
     wiping
    0.11
     wipes
    0.11
     wiped
    0.10
     Swipe
    0.09
    wipe
    0.08
    script
    0.08
     mop
    0.07
    dig
    0.07
     intelligent
    0.07
    Activations Density 0.003%

    No Known Activations