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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12718
    Prev
    Next
    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash

    This neuron detects contrastive conjunctions—specifically “But” (and its variants like “However”) when used to signal a turn or contrast in the discourse.

    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
    ‌آ
    -0.07
    opsy
    -0.07
    正式
    -0.07
    spa
    -0.07
    ANG
    -0.06
    873
    -0.06
    (ST
    -0.06
    IRCLE
    -0.06
    -and
    -0.06
     ا
    -0.06
    POSITIVE LOGITS
     But
    0.12
    But
    0.11
    .But
    0.09
    .pushButton
    0.07
    .but
    0.07
    。但
    0.07
    .bucket
    0.07
    "But
    0.07
    ').'</
    0.07
    .manager
    0.07
    Activations Density 0.051%

    No Known Activations