© 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. 127491
    Prev
    Next
    INDEX
    Explanations

    phrases indicating certainty and doubt in 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
    perator
    -0.07
    ÙĪÙĦا
    -0.07
    eldom
    -0.06
    edList
    -0.06
    emon
    -0.06
    âĶIJ
    -0.06
    лаÑĢа
    -0.06
     philosoph
    -0.06
    bote
    -0.06
    changer
    -0.06
    POSITIVE LOGITS
     researchers
    0.09
     scientists
    0.09
    research
    0.09
     research
    0.08
     Discovery
    0.08
     researcher
    0.08
     discoveries
    0.08
    ç§ijåѦ
    0.07
     studies
    0.07
     modern
    0.07
    Activations Density 0.028%

    No Known Activations