© 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. 120231
    Prev
    Next
    INDEX
    Explanations

    references to visual aids and diagrams in educational content

    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
    nea
    -0.07
    еко
    -0.06
     Determin
    -0.06
    xn
    -0.06
    vet
    -0.06
     determin
    -0.06
    assa
    -0.06
    stice
    -0.06
     skl
    -0.06
    ulado
    -0.06
    POSITIVE LOGITS
     visualization
    0.10
     Visualization
    0.10
     concrete
    0.09
    physical
    0.09
     physical
    0.09
     Concrete
    0.09
    visualization
    0.09
     tangible
    0.09
    _visual
    0.08
     visual
    0.08
    Activations Density 0.042%

    No Known Activations