© 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. 110564
    Prev
    Next
    INDEX
    Explanations

    manicure/polish

    np_max-act · gemini-2.0-flash

    The neuron is tuned to identify terms related to nail care and nail art (e.g. “nail,” “art,” “manicure,” “polish,” “tutorials,” “glitter,” “gradient”).

    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
    콩
    -0.07
    aub
    -0.06
     keine
    -0.06
    .assertNotNull
    -0.06
    abcdefghijklmnop
    -0.06
     teg
    -0.06
    ableOpacity
    -0.06
    nf
    -0.06
    ทย
    -0.06
     atrav
    -0.06
    POSITIVE LOGITS
     내용
    0.07
    ea
    0.06
     crafting
    0.06
     femin
    0.06
    845
    0.06
    ।↵↵
    0.06
     tempting
    0.06
     maxlength
    0.06
    álním
    0.06
    anggan
    0.06
    Activations Density 0.004%

    No Known Activations