© 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. 5-LLAMASCOPE-RES-131K
    11. 126882
    Prev
    Next
    INDEX
    Explanations

    locations and conditions related to uneven or problematic surfaces

    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
    UEL
    -0.08
    473
    -0.07
    \<^
    -0.07
    etin
    -0.07
     Hib
    -0.06
    orex
    -0.06
    oload
    -0.06
    dden
    -0.06
    hawk
    -0.06
     Ãľn
    -0.06
    POSITIVE LOGITS
     Areas
    0.07
    ilib
    0.07
     spots
    0.07
     areas
    0.06
    ojis
    0.06
    .psi
    0.06
    ocaust
    0.06
     pip
    0.06
     shr
    0.06
     onBind
    0.06
    Activations Density 0.062%

    No Known Activations