© 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. 129565
    Prev
    Next
    INDEX
    Explanations

    phrases related to predictions and uncertainty in outcomes

    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
     sometimes
    -0.08
    elay
    -0.07
    Sometimes
    -0.07
    sometimes
    -0.07
    udu
    -0.07
    almost
    -0.07
     Sometimes
    -0.07
    zan
    -0.07
    idir
    -0.06
     mos
    -0.06
    POSITIVE LOGITS
     unless
    0.15
     anything
    0.13
    unless
    0.12
     anymore
    0.12
     any
    0.12
     Unless
    0.10
    anything
    0.10
    Unless
    0.10
     EVER
    0.10
     Anything
    0.09
    Activations Density 0.054%

    No Known Activations