© 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. 15-LLAMASCOPE-RES-131K
    11. 87879
    Prev
    Next
    INDEX
    Explanations

    terms related to transaction processes and monitoring

    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
    zu
    -0.07
     of
    -0.06
     Barbar
    -0.06
     Buchanan
    -0.06
     lo
    -0.06
    ENS
    -0.06
     bi
    -0.06
    Ä©
    -0.06
    [++
    -0.06
     self
    -0.05
    POSITIVE LOGITS
    azı
    0.08
    .tc
    0.07
    edar
    0.07
    ĥn
    0.07
    arım
    0.07
    izon
    0.07
    orgia
    0.07
    문ìĿĦ
    0.07
    hest
    0.07
    ombo
    0.07
    Activations Density 0.026%

    No Known Activations