© 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. 5142
    Prev
    Next
    INDEX
    Explanations

    activities related to travel and exploration

    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
     dak
    -0.08
    ideon
    -0.08
    /workspace
    -0.07
     shoreline
    -0.07
    aldi
    -0.07
     sog
    -0.07
     semiclass
    -0.07
    ANJI
    -0.07
    osy
    -0.07
    ë¹Ļ
    -0.07
    POSITIVE LOGITS
     shallow
    0.08
     depth
    0.08
    depth
    0.08
     depths
    0.08
     Depth
    0.07
     Depths
    0.07
    Depth
    0.07
     cle
    0.07
    _depth
    0.07
    .depth
    0.07
    Activations Density 0.031%

    No Known Activations