© 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. 15-LLAMASCOPE-RES-131K
    11. 1369
    Prev
    Next
    INDEX
    Explanations

    chronological references to events and time periods

    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
     extras
    -0.08
     eventually
    -0.08
     afterwards
    -0.07
     eventual
    -0.07
     afterward
    -0.07
    extras
    -0.07
    erville
    -0.07
    eya
    -0.07
     nakonec
    -0.06
     Afterwards
    -0.06
    POSITIVE LOGITS
     earlier
    0.15
     Earlier
    0.13
    Earlier
    0.12
    ear
    0.11
     had
    0.09
     hadn
    0.09
    had
    0.09
     previous
    0.08
    previous
    0.08
     preceding
    0.08
    Activations Density 0.025%

    No Known Activations