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. 40534
    Prev
    Next
    INDEX
    Explanations

    graph scales

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of adjusting or equalizing the scales (aspect ratio) of the x- and y-axes in plotting code.

    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
    İZ
    -0.07
    Wilson
    -0.07
    OID
    -0.06
    Ж
    -0.06
    Brown
    -0.06
    Van
    -0.06
    (){
    -0.06
     人
    -0.06
    _Out
    -0.06
    ись
    -0.06
    POSITIVE LOGITS
     TN
    0.06
     aku
    0.06
     Presents
    0.06
     đem
    0.06
     честь
    0.06
    ็น
    0.06
    �江
    0.06
     Ae
    0.06
    emento
    0.06
     شاخه
    0.06
    Activations Density 0.018%

    No Known Activations