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. 86121
    Prev
    Next
    INDEX
    Explanations

    screenshots and code snippets

    np_max-act · gemini-2.0-flash

    The neuron fires on pieces of URLs—especially domain‐name fragments and short path tokens.

    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
     EXPER
    -0.07
    .");
    ↵
    -0.06
    (|
    -0.06
     robotic
    -0.06
     substr
    -0.06
     twig
    -0.06
     interven
    -0.06
     geometry
    -0.06
    Memcpy
    -0.06
     persuasive
    -0.06
    POSITIVE LOGITS
    _pic
    0.07
     обличчя
    0.07
    value
    0.06
     Nas
    0.06
    EOF
    0.06
    _decorator
    0.06
     ayn
    0.06
    (Room
    0.06
    documentation
    0.06
    ForegroundColor
    0.06
    Activations Density 0.009%

    No Known Activations