© 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. 93769
    Prev
    Next
    INDEX
    Explanations

    circular dichroism experiments

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of protein secondary‐structure analysis—especially terms around circular dichroism spectroscopy and conformational changes.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    scientific terms and phrases related to protein stability and structure.

    oai_token-act-pair · gpt-4o-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
     contaminated
    -0.06
     믿
    -0.06
    Buf
    -0.06
     ček
    -0.06
    authors
    -0.06
     Lorenzo
    -0.06
     yapılması
    -0.06
    contrast
    -0.06
     refrain
    -0.06
    الية
    -0.06
    POSITIVE LOGITS
    usable
    0.07
    …ط
    0.06
    .Create
    0.06
     valor
    0.06
    ’:
    0.06
     Dresses
    0.06
     alloc
    0.06
     ELSE
    0.06
     dış
    0.06
     Think
    0.06
    Activations Density 0.002%

    No Known Activations