© 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. 6033
    Prev
    Next
    INDEX
    Explanations

    Text

    np_max-act · gemini-2.0-flash

    This neuron lights up on common grammatical function words—especially the definite article “the” and auxiliary verbs like “are” and “will.”

    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
     Cres
    -0.07
    вар
    -0.06
    忆
    -0.06
    ня
    -0.06
    -prop
    -0.06
     geometric
    -0.06
     retries
    -0.06
     Mex
    -0.06
     Pep
    -0.06
    /people
    -0.06
    POSITIVE LOGITS
     flooding
    0.07
    udoku
    0.06
     seja
    0.06
     overcrow
    0.06
    تان
    0.06
     uncover
    0.06
     {\↵
    0.06
    }$
    0.06
     drifting
    0.06
    ใหม
    0.06
    Activations Density 0.111%

    No Known Activations