© 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 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. 38226
    Prev
    Next
    INDEX
    Explanations

    highlight

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of “highlight” or “highlights,” marking sections that introduce trip highlights.

    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
     Abd
    -0.06
    gen
    -0.06
     getById
    -0.06
    Ocean
    -0.06
     початку
    -0.06
     terminology
    -0.06
    _recent
    -0.06
     Spam
    -0.06
     Ocean
    -0.06
     Reputation
    -0.06
    POSITIVE LOGITS
    Highlights
    0.08
     highlights
    0.07
     Hib
    0.07
     Peg
    0.07
     mayoría
    0.07
     Exhibit
    0.07
     Highlights
    0.07
     barely
    0.07
     çı
    0.07
     Already
    0.07
    Activations Density 0.008%

    No Known Activations