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. 86182
    Prev
    Next
    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash

    This neuron fires on the headings or section titles (often including numbered labels or post‐style titles) that introduce new segments in a blog/review format.

    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
    OL
    -0.07
    _OBJ
    -0.07
     mask
    -0.07
     simply
    -0.07
    oney
    -0.06
     Wilson
    -0.06
     bust
    -0.06
     autoimmune
    -0.06
     leases
    -0.06
     indica
    -0.06
    POSITIVE LOGITS
    ////////////////////////////////////////////////////////////////////////////////////////////////
    0.06
     товарів
    0.06
     많은
    0.06
    ा।↵↵
    0.06
     ctxt
    0.06
    ')}}↵
    0.06
    ivariate
    0.06
    ΙΚΗΣ
    0.06
    InstantiationException
    0.06
    Reminder
    0.06
    Activations Density 0.240%

    No Known Activations