© 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. 93286
    Prev
    Next
    INDEX
    Explanations

    words indicating processes or actions that involve change, improvement, or development

    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
    stin
    -0.08
    lue
    -0.06
     thrust
    -0.06
    889
    -0.06
    Theory
    -0.06
     beginning
    -0.06
    å±ŀäºİ
    -0.06
    ecast
    -0.06
    ifik
    -0.05
     Beginning
    -0.05
    POSITIVE LOGITS
     design
    0.09
    è¨Ńè¨Ī
    0.08
     designed
    0.08
    idle
    0.08
    Įĵ
    0.07
     vet
    0.07
    设计
    0.07
    ERG
    0.07
     diseñ
    0.07
     tasar
    0.07
    Activations Density 0.017%

    No Known Activations