© 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. 60999
    Prev
    Next
    INDEX
    Explanations

    financial metrics and related data points

    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
    [__
    -0.10
     dán
    -0.08
    esses
    -0.08
    èµı
    -0.07
    SURE
    -0.07
     airs
    -0.07
    OLVE
    -0.07
    ZA
    -0.07
    باد
    -0.07
    .catch
    -0.07
    POSITIVE LOGITS
     continuing
    0.08
     future
    0.07
     continue
    0.07
     outlook
    0.07
     plans
    0.07
    anko
    0.07
     continued
    0.06
     Outlook
    0.06
     inventory
    0.06
     Spotlight
    0.06
    Activations Density 0.020%

    No Known Activations