© 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 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. 130841
    Prev
    Next
    INDEX
    Explanations

    terms related to vehicle fuel efficiency and official performance metrics

    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
    otti
    -0.06
    um
    -0.06
    atica
    -0.06
     Haz
    -0.06
     st
    -0.06
     turn
    -0.06
     double
    -0.05
    itech
    -0.05
     t
    -0.05
    ayers
    -0.05
    POSITIVE LOGITS
    formace
    0.09
    .sul
    0.08
    LEV
    0.08
    ãĥ¼ãĥŃ
    0.08
    accordion
    0.07
    stras
    0.07
    webtoken
    0.07
    RAP
    0.07
    .useState
    0.07
    unately
    0.07
    Activations Density 0.000%

    No Known Activations