© 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. 15-LLAMASCOPE-RES-131K
    11. 87443
    Prev
    Next
    INDEX
    Explanations

    mathematical variables or constants referenced in equations

    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
     Dah
    -0.06
    --------------------------------------------------------------------------↵
    -0.06
     Oliver
    -0.06
    /print
    -0.06
    leur
    -0.06
    aspect
    -0.06
     Wend
    -0.05
     kn
    -0.05
     current
    -0.05
    eder
    -0.05
    POSITIVE LOGITS
    ë¶Ī
    0.07
    \OptionsResolver
    0.07
    ãĥ«ãĥī
    0.07
     didSet
    0.07
    ä¹ħ
    0.07
    alles
    0.07
    ÙĪرÙĩ
    0.06
    ehir
    0.06
    dealloc
    0.06
    оÑĢон
    0.06
    Activations Density 0.000%

    No Known Activations