© 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. 89451
    Prev
    Next
    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash

    instructions related to teaching young children about shapes in art.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron appears to be inactive—it never responds (i.e. it doesn’t detect any pattern).

    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
    鎮
    -0.07
     Job
    -0.06
    άβ
    -0.06
     Seen
    -0.06
     unseen
    -0.06
     건
    -0.06
     darker
    -0.06
    Pop
    -0.06
    yor
    -0.06
    ijd
    -0.06
    POSITIVE LOGITS
    .public
    0.07
    .labels
    0.07
    -election
    0.06
    CLUDE
    0.06
     yanlış
    0.06
    crypt
    0.06
     lands
    0.06
     لذا
    0.06
     Cutter
    0.06
    ={()
    0.06
    Activations Density 0.050%

    No Known Activations