© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 72194
    Prev
    Next
    INDEX
    Explanations

    differences

    np_max-act · gemini-2.0-flash

    This neuron detects words that signal contrast or diversity—comparative or descriptive terms like “different,” “diverse,” “varied,” and similar.

    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
    щ
    -0.06
     icmp
    -0.06
    640
    -0.06
    rotch
    -0.05
     denn
    -0.05
    _REASON
    -0.05
     참고
    -0.05
    .Dropout
    -0.05
    bled
    -0.05
    (token
    -0.05
    POSITIVE LOGITS
    periment
    0.08
    StringValue
    0.07
     تصم
    0.07
    กำ
    0.07
     neuken
    0.07
     сна
    0.07
    окрема
    0.07
    fav
    0.07
     Utf
    0.07
     индивиду
    0.06
    Activations Density 0.032%

    No Known Activations