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. 40643
    Prev
    Next
    INDEX
    Explanations

    your

    np_max-act · gemini-2.0-flash

    This neuron fires on the “at your option” phrase commonly found in GNU license boilerplate.

    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
     Auditor
    -0.07
    ipation
    -0.07
    _calls
    -0.06
    ())),
    -0.06
     CLL
    -0.06
    West
    -0.06
     lur
    -0.06
     react
    -0.06
    _INTEGER
    -0.06
    ANY
    -0.06
    POSITIVE LOGITS
    辞
    0.09
    的一
    0.07
     filesystem
    0.07
    .xtext
    0.07
     socialism
    0.06
    词
    0.06
    شب
    0.06
    └
    0.06
    งใน
    0.06
     формування
    0.06
    Activations Density 0.002%

    No Known Activations