© 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. 106574
    Prev
    Next
    INDEX
    Explanations

    references to string theory and higher-dimensional physics concepts

    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
     Edmonton
    -0.06
     spectral
    -0.06
     spect
    -0.06
     spar
    -0.06
     Ships
    -0.06
     Dahl
    -0.06
     ApiException
    -0.06
     Saul
    -0.06
     SelectList
    -0.06
    .ca
    -0.06
    POSITIVE LOGITS
    brane
    0.09
    ãĤ¤ãĤ¯
    0.07
    gv
    0.07
     br
    0.07
    _COMPAT
    0.07
     Barbar
    0.07
    Recognizer
    0.07
    ulis
    0.07
    оло
    0.07
     Randall
    0.06
    Activations Density 0.021%

    No Known Activations