© 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. 41512
    Prev
    Next
    INDEX
    Explanations

    relationships and comparisons between different entities or concepts

    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
     дÑĢÑĥгого
    -0.06
    ÑĪиб
    -0.06
    920
    -0.06
    ss
    -0.06
    eka
    -0.06
    (and
    -0.06
    mir
    -0.06
     companion
    -0.05
    udi
    -0.05
     gren
    -0.05
    POSITIVE LOGITS
     versus
    0.11
     sexes
    0.10
     two
    0.10
     respectively
    0.09
     vs
    0.09
    两个
    0.09
     different
    0.09
     две
    0.09
     beiden
    0.09
     halves
    0.08
    Activations Density 0.124%

    No Known Activations