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. 130728
    Prev
    Next
    INDEX
    Explanations

    Portuguese fragments

    np_max-act · gemini-2.0-flash

    This neuron fires on Portuguese function words (especially prepositions and articles such as “pelo,” “às,” “na,” “das,” “da,” etc.).

    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
    c
    -0.09
    k
    -0.08
    z
    -0.07
    you
    -0.07
    C
    -0.07
    ;c
    -0.07
     "
    -0.07
    h
    -0.07
     JUST
    -0.07
    obutton
    -0.07
    POSITIVE LOGITS
     pela
    0.10
     della
    0.09
     nella
    0.08
     dalla
    0.08
     da
    0.08
     del
    0.08
    InThe
    0.08
     Nel
    0.07
     Da
    0.07
     across
    0.07
    Activations Density 0.124%

    No Known Activations