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. 130612
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron is looking for Wikipedia “Category:” metadata lines (e.g. category tags like “People of the Tudor period”).

    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
    ule
    -0.07
    На
    -0.06
     فإن
    -0.06
    .Parser
    -0.06
    -work
    -0.06
    .Points
    -0.06
    >P
    -0.06
    eel
    -0.06
    Turning
    -0.06
    чних
    -0.06
    POSITIVE LOGITS
     Chỉ
    0.07
    ิ่
    0.07
    Guid
    0.06
    ρχ
    0.06
     do
    0.06
    ξεις
    0.06
     chop
    0.06
     encount
    0.06
     mitt
    0.06
     Dell
    0.06
    Activations Density 0.005%

    No Known Activations