© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 77608
    Prev
    Next
    INDEX
    Explanations

    key phrases related to uncertainty and conditions

    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
    oller
    -0.07
    itten
    -0.07
    μοί
    -0.07
    875
    -0.07
    iram
    -0.06
    ucha
    -0.06
    æŁ´
    -0.06
    aida
    -0.06
    imal
    -0.06
    ulla
    -0.06
    POSITIVE LOGITS
     sometimes
    0.10
     often
    0.08
     merely
    0.08
    sometimes
    0.08
     presence
    0.08
     mere
    0.08
     simply
    0.07
     may
    0.07
     Sometimes
    0.07
     plenty
    0.07
    Activations Density 0.046%

    No Known Activations