© 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 EvalsExportsinterp-engineNEWAPI 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. 28047
    Prev
    Next
    INDEX
    Explanations

    financial figures and business revenue details

    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
     action
    -0.07
     ACTION
    -0.06
     upright
    -0.06
     backwards
    -0.06
    ollect
    -0.06
     backward
    -0.05
     Action
    -0.05
    poon
    -0.05
     pack
    -0.05
     syn
    -0.05
    POSITIVE LOGITS
     revenues
    0.13
     revenue
    0.11
     Revenue
    0.09
    Revenue
    0.08
     reven
    0.08
    -turn
    0.08
     annual
    0.08
     gross
    0.08
    gross
    0.08
     sales
    0.08
    Activations Density 0.021%

    No Known Activations