© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92297
    Prev
    Next
    INDEX
    Explanations

    patent claims and descriptions

    np_max-act · gemini-2.0-flash

    This neuron responds strongly to technical process‐and‐apparatus vocabulary—terms like “method,” “apparatus,” “manufacturing,” “components,” “molding,” “tools,” and similar—that introduce or describe manufacturing processes.

    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
     dips
    -0.07
    ána
    -0.06
    igmat
    -0.06
     unchecked
    -0.06
     unl
    -0.06
     visa
    -0.06
    weapon
    -0.06
     puzz
    -0.06
     pud
    -0.06
     minors
    -0.06
    POSITIVE LOGITS
    .bean
    0.07
    빛
    0.06
     bleibt
    0.06
    Seeder
    0.06
    ibilidad
    0.06
     muchos
    0.06
     elevate
    0.06
    erchant
    0.06
    .Areas
    0.06
    Rotor
    0.06
    Activations Density 0.165%

    No Known Activations