© 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. 17-LLAMASCOPE-RES-131K
    11. 17882
    Prev
    Next
    INDEX
    Explanations

    technical mathematical terms related to functions and mappings

    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
    ohn
    -0.08
    bjerg
    -0.07
    assin
    -0.07
    ncia
    -0.07
    pora
    -0.07
    isu
    -0.07
     jl
    -0.07
     Herz
    -0.07
     klu
    -0.07
    zew
    -0.07
    POSITIVE LOGITS
    elop
    0.06
    issy
    0.06
     ->
    0.06
    ä¹¾
    0.06
     Sever
    0.06
     spotting
    0.05
    obile
    0.05
     Replacement
    0.05
    -t
    0.05
     converted
    0.05
    Activations Density 0.097%

    No Known Activations