© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127898
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific modeling and environmental processes

    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
    ιαν
    -0.07
    нож
    -0.07
    沿
    -0.07
    celik
    -0.06
    cki
    -0.06
    زÙĬ
    -0.06
    .Attach
    -0.06
    ìķ
    -0.06
    sak
    -0.06
    _dd
    -0.06
    POSITIVE LOGITS
     larger
    0.16
     macro
    0.16
    macro
    0.15
     large
    0.15
     Larger
    0.14
     macros
    0.14
    å®ı
    0.14
     big
    0.13
     Large
    0.13
     Macro
    0.13
    Activations Density 0.124%

    No Known Activations