© 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. 7309
    Prev
    Next
    INDEX
    Explanations

    S

    np_max-act · gemini-2.0-flash

    The neuron did not activate on any of the tokens in these excerpts, suggesting it either looks for a very specific pattern that didn’t occur here or is effectively “off” on this text.

    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
    acağım
    -0.07
    Ent
    -0.06
    лова
    -0.06
    ेद
    -0.06
     zaměř
    -0.06
    .LabelControl
    -0.06
    동안
    -0.06
    computer
    -0.06
    [selected
    -0.06
    ulerAngles
    -0.06
    POSITIVE LOGITS
    .blog
    0.07
     projectiles
    0.07
    normalized
    0.06
     localization
    0.06
     narration
    0.06
    Cloud
    0.06
    shield
    0.06
    	resp
    0.06
    =max
    0.06
     embarrassment
    0.06
    Activations Density 0.002%

    No Known Activations