© 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. 109158
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    scientific classification and descriptions of plant species.

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

    The neuron specializes in spotting taxonomic “family” statements, i.e. the “in the … family” phrase in species descriptions.

    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
     programmes
    -0.07
     Fulton
    -0.07
     بتن
    -0.06
     чего
    -0.06
     cel
    -0.06
    ,row
    -0.06
    ']]);↵
    -0.06
     pageCount
    -0.06
     kob
    -0.06
    alten
    -0.06
    POSITIVE LOGITS
    	offset
    0.07
    Posting
    0.07
    隆
    0.07
     homosexual
    0.07
     президент
    0.06
    Disposed
    0.06
     소개
    0.06
     Đại
    0.06
     výraz
    0.06
    ุตสาหกรรม
    0.06
    Activations Density 0.002%

    No Known Activations