© 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. 119264
    Prev
    Next
    INDEX
    Explanations

    expressions related to uncertainty and speculation

    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
    ffa
    -0.07
    inder
    -0.06
     stands
    -0.06
    ÏĢή
    -0.06
     lit
    -0.06
     اÙĦÙĪ
    -0.06
    rak
    -0.05
    ader
    -0.05
    aris
    -0.05
    day
    -0.05
    POSITIVE LOGITS
     somehow
    0.11
     somewhere
    0.09
     somew
    0.08
    something
    0.07
     maybe
    0.07
    ilha
    0.07
    даÑħ
    0.07
    ksam
    0.07
    ought
    0.07
     algun
    0.07
    Activations Density 0.011%

    No Known Activations