© 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 EvalsExportsinterp-engineNEWAPI 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. 57718
    Prev
    Next
    INDEX
    Explanations

    active

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “active” (and close variants like “actively” or “activist”), i.e. tokens indicating active involvement.

    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
     WC
    -0.06
    Ware
    -0.06
    -work
    -0.06
     Boehner
    -0.06
     bet
    -0.06
     ce
    -0.06
    best
    -0.06
    buy
    -0.06
     generic
    -0.06
     ultimately
    -0.06
    POSITIVE LOGITS
     active
    0.10
     Active
    0.09
     Actions
    0.08
     activity
    0.08
     exercising
    0.08
     Silent
    0.08
     Toolkit
    0.08
    Keywords
    0.07
    ظˆط
    0.07
     brisk
    0.07
    Activations Density 0.024%

    No Known Activations