© 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. 73164
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to business and marketing strategies

    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
    ibold
    -0.06
    /react
    -0.06
     Wright
    -0.06
    ifen
    -0.06
    enso
    -0.06
    sb
    -0.06
     Rim
    -0.06
     village
    -0.05
    uro
    -0.05
     notification
    -0.05
    POSITIVE LOGITS
     Sales
    0.13
     sales
    0.13
    -sales
    0.12
    Sales
    0.11
     salesman
    0.11
    sales
    0.11
    éĶĢåĶ®
    0.10
    _sales
    0.09
     satÄ±ÅŁ
    0.08
     Territories
    0.08
    Activations Density 0.031%

    No Known Activations