© 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. 126654
    Prev
    Next
    INDEX
    Explanations

    numerical data, specifically timestamps and numerical values related to events or statuses

    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
    rani
    -0.09
    assi
    -0.07
     CircularProgress
    -0.07
    ARS
    -0.07
    ctrine
    -0.07
    cestor
    -0.07
    agna
    -0.07
    -helper
    -0.07
    ledo
    -0.07
    θα
    -0.07
    POSITIVE LOGITS
    ì°Į
    0.06
    arem
    0.06
    itz
    0.06
    blast
    0.06
    Profiler
    0.06
     Agricult
    0.05
    itm
    0.05
     Isle
    0.05
     Ballard
    0.05
     confirmation
    0.05
    Activations Density 0.005%

    No Known Activations