© 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. 40419
    Prev
    Next
    INDEX
    Explanations

    references to time periods and scheduling events

    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
     dawn
    -0.08
    exus
    -0.07
    ource
    -0.07
    ynos
    -0.07
    owler
    -0.07
    åĩĮ
    -0.07
    ayd
    -0.07
    camp
    -0.07
    mÃŃ
    -0.06
    anchise
    -0.06
    POSITIVE LOGITS
     weekly
    0.08
    anford
    0.07
    adt
    0.07
     susp
    0.07
    con
    0.07
    weekly
    0.06
    artic
    0.06
     Wochen
    0.06
     à¤ħà¤Ĺल
    0.06
    bilt
    0.06
    Activations Density 0.053%

    No Known Activations