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. 130285
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    The neuron reliably spotlights comment lines in configuration or build files (i.e. lines beginning with “#”).

    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
     Felix
    -0.08
     soup
    -0.07
     amateur
    -0.07
    坊
    -0.07
     avalanche
    -0.07
     вероят
    -0.07
    ์พ
    -0.07
    Chi
    -0.07
     хозя
    -0.06
    นคร
    -0.06
    POSITIVE LOGITS
     â
    0.07
    linkplain
    0.07
    (http
    0.06
    ;j
    0.06
     git
    0.06
    |wx
    0.06
    Filed
    0.06
    .wp
    0.06
    :w
    0.06
    .Random
    0.06
    Activations Density 0.011%

    No Known Activations