© 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 EvalsExportsinterp-engineNEWAPI 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. 92971
    Prev
    Next
    INDEX
    Explanations

    mentions of specific weeks in a schedule or timeframe

    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
    ulse
    -0.07
    resh
    -0.07
    /lg
    -0.07
    suite
    -0.06
    ving
    -0.06
    ANGO
    -0.06
    owell
    -0.06
     chemin
    -0.06
    uger
    -0.06
    WAY
    -0.06
    POSITIVE LOGITS
    /month
    0.16
    æľ«
    0.11
    -long
    0.11
    night
    0.10
    ender
    0.10
    long
    0.09
    -end
    0.09
    ends
    0.09
    enden
    0.09
    ened
    0.08
    Activations Density 0.038%

    No Known Activations