© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56844
    Prev
    Next
    INDEX
    Explanations

    instances of unexpected scenarios or unusual statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    turnstile
    -0.07
     Leer
    -0.07
    ugi
    -0.07
    ebo
    -0.07
    allery
    -0.07
    oine
    -0.06
    .IContainer
    -0.06
    .updateDynamic
    -0.06
    .Skin
    -0.06
    ente
    -0.06
    POSITIVE LOGITS
     rare
    0.39
     rarity
    0.35
     Rare
    0.35
    Rare
    0.31
     rarely
    0.26
     uncommon
    0.24
     ÑĢед
    0.22
     rar
    0.21
     seldom
    0.20
     unusual
    0.20
    Activations Density 0.201%

    No Known Activations