© 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. 16980
    Prev
    Next
    INDEX
    Explanations

    negations and words indicating exceptions or limitations

    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
    ikel
    -0.07
    __/
    -0.07
    clar
    -0.07
    acie
    -0.07
    stile
    -0.07
    ÏĥÏĢ
    -0.07
    ibold
    -0.06
    issors
    -0.06
    ứng
    -0.06
    trinsic
    -0.06
    POSITIVE LOGITS
     necessarily
    0.09
     perfect
    0.09
     zwar
    0.07
     directly
    0.07
    alla
    0.07
     exact
    0.07
    alace
    0.07
     ideal
    0.07
     Perfect
    0.06
    aller
    0.06
    Activations Density 0.037%

    No Known Activations