© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 29080
    Prev
    Next
    INDEX
    Explanations

    instances of surprise or disbelief

    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
    리ìĸ´
    -0.07
    zk
    -0.07
    ï¿
    -0.06
    amet
    -0.06
     quitting
    -0.06
    kus
    -0.06
    quit
    -0.06
     íĴ
    -0.06
    UTES
    -0.06
    uctive
    -0.06
    POSITIVE LOGITS
    erver
    0.07
    oi
    0.07
    lä
    0.07
    .um
    0.06
    ieber
    0.06
    oq
    0.06
     oh
    0.06
    si
    0.06
    ellido
    0.06
    osti
    0.06
    Activations Density 0.000%

    No Known Activations