© 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. 38941
    Prev
    Next
    INDEX
    Explanations

    Scientific papers

    np_max-act · gemini-2.0-flash

    This neuron detects specialized chemical terms referring to emulsifiers and interface‐active substances in colloidal or emulsion descriptions.

    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
     pared
    -0.06
    apist
    -0.06
     COM
    -0.06
     Walters
    -0.06
    qr
    -0.06
     undisclosed
    -0.06
     Roulette
    -0.06
     Wilhelm
    -0.06
    olving
    -0.06
     culprit
    -0.06
    POSITIVE LOGITS
    민주
    0.07
    емати
    0.07
     closures
    0.06
    standard
    0.06
    queueReusable
    0.06
     csrf
    0.06
     staffer
    0.06
    ordable
    0.06
    utex
    0.06
     molecules
    0.06
    Activations Density 0.043%

    No Known Activations