© 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. 125945
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    The neuron fires on little “proof‐step” words—connectives like “by,” “since,” “then,” and “follows” that introduce justification or inference steps in a mathematical argument.

    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
     showError
    -0.06
     proficient
    -0.06
     กร
    -0.06
     sciences
    -0.06
    говор
    -0.06
     Healthcare
    -0.06
     gains
    -0.06
     alphabet
    -0.06
     graduates
    -0.06
    ialect
    -0.06
    POSITIVE LOGITS
    /big
    0.06
     flew
    0.06
    bd
    0.06
     arbe
    0.06
    意义
    0.06
     Savaşı
    0.06
     піс
    0.06
    lid
    0.06
     Ngb
    0.06
     tostring
    0.06
    Activations Density 0.021%

    No Known Activations