© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 38518
    Prev
    Next
    INDEX
    Explanations

    Most

    np_max-act · gemini-2.0-flash

    This neuron detects sentence- or section-initial tokens, i.e. capitalized words and headings (including titles and the first word after a colon or at paragraph starts).

    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
    获
    -0.07
    lin
    -0.06
    核
    -0.06
    /device
    -0.06
     absence
    -0.06
    /body
    -0.06
     계획
    -0.06
    --)
    -0.06
     PLA
    -0.06
    -food
    -0.06
    POSITIVE LOGITS
    駅
    0.07
    ulfill
    0.07
     Wordpress
    0.06
     configured
    0.06
    	req
    0.06
     cigars
    0.06
     вв
    0.06
     esports
    0.06
    ']]],↵
    0.06
    Sum
    0.06
    Activations Density 0.015%

    No Known Activations