© 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. 91179
    Prev
    Next
    INDEX
    Explanations

    UI buttons/actions

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that are part of icon class names (e.g., “icon-plus-sign,” “fa-upload,” “icon-trash,” etc.) in HTML/CSS markup.

    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
     MF
    -0.08
    RESS
    -0.07
     Nice
    -0.07
    retch
    -0.07
    resp
    -0.07
    Ascii
    -0.06
    Xi
    -0.06
    یره
    -0.06
    Aus
    -0.06
    RI
    -0.06
    POSITIVE LOGITS
     palabras
    0.08
     scaleFactor
    0.06
    [opt
    0.06
    STALL
    0.06
     acción
    0.06
    -selected
    0.06
     (::
    0.06
     BAS
    0.06
    /sbin
    0.06
     azalt
    0.06
    Activations Density 0.004%

    No Known Activations