© 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. 15-RESID-POST-AA
    11. 92784
    Prev
    Next
    INDEX
    Explanations

    order

    np_max-act · gemini-2.0-flash

    phrases that describe sorting or ordering (words like "sort", "increasing/descending/ascending/decreasing", "order").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subconscious
    -0.07
     frustr
    -0.07
     нек
    -0.07
     disco
    -0.07
     patience
    -0.06
     služeb
    -0.06
     Ulus
    -0.06
     recal
    -0.06
     deren
    -0.06
     ludicrous
    -0.06
    POSITIVE LOGITS
    .IP
    0.07
    ISTICS
    0.06
     Prop
    0.06
    덕
    0.06
    (distance
    0.06
    PHONE
    0.06
    measurement
    0.06
    anny
    0.06
     Crowley
    0.06
    .mx
    0.06
    Activations Density 0.002%

    No Known Activations