© 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. 73731
    Prev
    Next
    INDEX
    Explanations

    terms related to manufacturing and machinery types

    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
    kle
    -0.07
    ozor
    -0.07
    razil
    -0.07
    ioned
    -0.07
    cobra
    -0.07
    ystack
    -0.07
    olec
    -0.06
    otten
    -0.06
    elocity
    -0.06
    [++
    -0.06
    POSITIVE LOGITS
    ata
    0.08
    alam
    0.06
     Vernon
    0.06
    ait
    0.06
    PP
    0.05
    IS
    0.05
     tr
    0.05
    geh
    0.05
    662
    0.05
     Cyr
    0.05
    Activations Density 0.004%

    No Known Activations