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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 68358
    Prev
    Next
    INDEX
    Explanations

    polish

    np_max-act · gemini-2.0-flash

    The neuron activates whenever the word “polish” (in any context) appears.

    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
    tein
    -0.07
     swung
    -0.07
     попада
    -0.07
     feed
    -0.07
    وجود
    -0.07
     Seg
    -0.07
     biome
    -0.07
    portunity
    -0.07
    aket
    -0.07
     motion
    -0.06
    POSITIVE LOGITS
     polished
    0.13
     polish
    0.11
     polishing
    0.10
     Polish
    0.09
    nish
    0.08
    ussy
    0.07
    FormsModule
    0.07
    وفي
    0.07
     offsetY
    0.07
     lavish
    0.07
    Activations Density 0.006%

    No Known Activations