Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 84562
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    This neuron detects single-letter Portuguese articles and similar one-letter function words (e.g. “a”, “o”, “as”).

    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
     ولي
    -0.09
    езульт
    -0.07
     Bern
    -0.07
     Cheng
    -0.07
    Lee
    -0.07
     rel
    -0.07
     Leon
    -0.07
     still
    -0.07
    Life
    -0.07
    IEL
    -0.07
    POSITIVE LOGITS
     The
    0.09
    The
    0.07
     Oc
    0.07
    p
    0.07
    0
    0.07
    AYOUT
    0.07
    AD
    0.07
    O
    0.07
     backing
    0.07
    	Q
    0.07
    Activations Density 0.079%

    No Known Activations