© 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. 80463
    Prev
    Next
    INDEX
    Explanations

    monetary and economic transactions or conditions

    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
     Hunters
    -0.06
     resale
    -0.06
     Hunter
    -0.06
    ugo
    -0.05
    mess
    -0.05
     spinning
    -0.05
    524
    -0.05
    -t
    -0.05
    nze
    -0.05
     Hollow
    -0.05
    POSITIVE LOGITS
     costs
    0.14
     Costs
    0.13
    Cost
    0.13
     COST
    0.12
    æĪIJæľ¬
    0.12
    cost
    0.12
     Cost
    0.12
     cost
    0.12
    _COST
    0.12
    _cost
    0.11
    Activations Density 0.066%

    No Known Activations