© 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. 87164
    Prev
    Next
    INDEX
    Explanations

    elements related to job application strategies and waste management services

    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
    erman
    -0.07
    ero
    -0.07
    åłĤ
    -0.07
    DOT
    -0.06
    $MESS
    -0.06
    icious
    -0.06
     bil
    -0.06
    ittel
    -0.06
     clin
    -0.06
     cod
    -0.05
    POSITIVE LOGITS
     bợi
    0.09
     by
    0.08
     oleh
    0.08
     Wyn
    0.08
    byt
    0.07
    utsche
    0.07
    ingleton
    0.06
    mart
    0.06
    [assembly
    0.06
    iren
    0.06
    Activations Density 0.028%

    No Known Activations