© 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. 84188
    Prev
    Next
    INDEX
    Explanations

    terms related to relativistic theories in physics

    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
    anax
    -0.08
    offline
    -0.07
    rupt
    -0.07
    igure
    -0.07
    eeper
    -0.07
    eyer
    -0.07
    ãĥ£
    -0.07
    iw
    -0.07
    osg
    -0.07
    екÑĤоÑĢ
    -0.07
    POSITIVE LOGITS
     relativ
    0.07
     rel
    0.07
    -rel
    0.07
     Rel
    0.07
    ized
    0.06
    ly
    0.06
    zed
    0.06
    (New
    0.06
    /world
    0.06
    /angular
    0.06
    Activations Density 0.003%

    No Known Activations