© 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. 57991
    Prev
    Next
    INDEX
    Explanations

    references to scheduling and operational status

    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
     retiring
    -0.07
     Tonight
    -0.07
    RET
    -0.07
     tonight
    -0.07
    éĢĢ
    -0.07
    Tonight
    -0.07
     nighttime
    -0.06
    ecut
    -0.06
     Drops
    -0.06
     drops
    -0.06
    POSITIVE LOGITS
     resume
    0.11
     resumed
    0.11
    復
    0.11
     resumes
    0.10
     Resume
    0.10
    æģ¢
    0.10
    _resume
    0.10
    .resume
    0.09
     recovery
    0.09
     comeback
    0.09
    Activations Density 0.067%

    No Known Activations