© 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. 80085
    Prev
    Next
    INDEX
    Explanations

    financial and economic metrics related to corporate performance and taxation

    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
    elen
    -0.07
    oot
    -0.06
    amp
    -0.06
    Inverse
    -0.06
     wastes
    -0.06
    earth
    -0.06
    allen
    -0.06
     Chap
    -0.05
     ambit
    -0.05
    eson
    -0.05
    POSITIVE LOGITS
     revenue
    0.21
     revenues
    0.18
     Revenue
    0.17
    Revenue
    0.16
     income
    0.11
     reven
    0.11
     proceeds
    0.10
    æĶ¶çĽĬ
    0.10
    æĶ¶åħ¥
    0.10
     доÑħод
    0.10
    Activations Density 0.091%

    No Known Activations