Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 40399
    Prev
    Next
    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash

    scientific terminology related to genetics and cytokines.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron responds to short uppercase letter sequences (like “BB,” “CC,” “TT,” “TC”) used as allele or genotype codes in genetic notation.

    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
    tour
    -0.06
     morb
    -0.06
     thousand
    -0.06
    DetailView
    -0.06
    King
    -0.06
    멘
    -0.06
     WaitFor
    -0.06
     imply
    -0.06
    ytt
    -0.06
    Tour
    -0.06
    POSITIVE LOGITS
     △
    0.06
    still
    0.06
     elic
    0.06
    请求
    0.06
     ה
    0.06
    ắc
    0.06
    /text
    0.06
    _LOG
    0.06
    Uses
    0.06
    :-------------</
    0.06
    Activations Density 0.086%

    No Known Activations