© 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. 6169
    Prev
    Next
    INDEX
    Explanations

    scientific contexts

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on specialized biological terms—especially cell types, organelles, and microorganisms (e.g. “erythrocyte,” “mitochondrial,” “bacterial”).

    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
    γή
    -0.07
    un
    -0.07
    failed
    -0.07
     attentive
    -0.06
    .When
    -0.06
    Lv
    -0.06
    ằng
    -0.06
    лим
    -0.06
    .my
    -0.06
    造成
    -0.06
    POSITIVE LOGITS
     Memor
    0.06
     Maid
    0.06
    ("""
    0.06
    -Col
    0.06
    "She
    0.06
     Freight
    0.06
    TRACT
    0.06
     grues
    0.06
    ;background
    0.06
     sor
    0.06
    Activations Density 0.214%

    No Known Activations