© 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. 57087
    Prev
    Next
    INDEX
    Explanations

    strict

    np_max-act · gemini-2.0-flash

    The neuron predominantly activates on the word “strict.”

    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
     fung
    -0.07
    ￥
    -0.07
     jente
    -0.07
    赢
    -0.07
     vending
    -0.07
     náz
    -0.07
     wav
    -0.07
     vå
    -0.07
     maliyet
    -0.06
     Berg
    -0.06
    POSITIVE LOGITS
     strictly
    0.13
     strict
    0.10
    Strict
    0.09
     XT
    0.08
    ict
    0.08
     stricter
    0.07
    AREST
    0.07
     thorough
    0.07
     Strict
    0.07
    [attr
    0.07
    Activations Density 0.005%

    No Known Activations