© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 83670
    Prev
    Next
    INDEX
    Explanations

    descriptive elements related to journeys and paths

    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
    nda
    -0.08
     meis
    -0.07
    ushima
    -0.07
    ÑĥÑĢн
    -0.07
    atee
    -0.07
    rna
    -0.07
    /hooks
    -0.07
    ographically
    -0.07
    .bid
    -0.07
    StateException
    -0.07
    POSITIVE LOGITS
     lines
    0.09
     route
    0.09
     line
    0.09
     along
    0.08
     axis
    0.08
    è·¯
    0.07
     path
    0.07
     edges
    0.07
     margins
    0.07
    line
    0.07
    Activations Density 0.023%

    No Known Activations