© 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. 87877
    Prev
    Next
    INDEX
    Explanations

    Technology and industries

    np_max-act · gemini-2.0-flash

    definitions and descriptions of artificial intelligence concepts.

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

    The neuron activates on words that name or point to domains, sectors, or fields of application (e.g. “applications,” “fields,” “setores”).

    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
    asper
    -0.06
    Quest
    -0.06
     ап
    -0.06
     Sha
    -0.06
     McGill
    -0.06
    	Schema
    -0.06
    _known
    -0.06
     Já
    -0.06
     Moh
    -0.06
    Thrown
    -0.06
    POSITIVE LOGITS
    सल
    0.07
     fleets
    0.06
    .isArray
    0.06
     увели
    0.06
     slashing
    0.06
    Increasing
    0.06
     dumb
    0.06
     backbone
    0.06
    одерж
    0.06
    rising
    0.06
    Activations Density 0.084%

    No Known Activations