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. 130569
    Prev
    Next
    INDEX
    Explanations

    .com

    np_max-act · gemini-2.0-flash

    The neuron identifies mentions of website domains (e.g., “.com,” “.net,” “.org”) in the text.

    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
    _updated
    -0.06
     fairy
    -0.06
     Trying
    -0.06
     누구
    -0.06
     Cons
    -0.06
     Claudia
    -0.06
     Quart
    -0.06
    Used
    -0.06
    _USED
    -0.06
     Rub
    -0.06
    POSITIVE LOGITS
    .com
    0.11
    .dk
    0.07
    .COM
    0.07
    .net
    0.07
     слова
    0.07
    .Net
    0.07
    .org
    0.07
     urlencode
    0.07
     verdiği
    0.07
    .gov
    0.07
    Activations Density 0.018%

    No Known Activations