© 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. 126889
    Prev
    Next
    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash

    This neuron activates on sentence-initial discourse markers and transitional phrases (e.g. “In view of,” “According to,” “Among,” etc.).

    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
    แ
    -0.07
    Visited
    -0.06
    Processed
    -0.06
     distur
    -0.06
    books
    -0.06
    аті
    -0.06
    .Hidden
    -0.06
    Average
    -0.06
    Hy
    -0.06
    .Weight
    -0.06
    POSITIVE LOGITS
     przez
    0.07
    umin
    0.06
    /team
    0.06
     olacağ
    0.06
    .cuda
    0.06
     ApplicationUser
    0.06
     इन
    0.06
     sefer
    0.06
    "]:↵
    0.06
    iswa
    0.06
    Activations Density 0.027%

    No Known Activations