© 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. 41685
    Prev
    Next
    INDEX
    Explanations

    terms related to assessment and evaluation

    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
    kowski
    -0.08
    idad
    -0.07
    utex
    -0.07
    ears
    -0.07
    eru
    -0.07
    onga
    -0.07
    ogle
    -0.07
    gui
    -0.06
    anio
    -0.06
    oming
    -0.06
    POSITIVE LOGITS
    edly
    0.12
    eting
    0.10
    ETING
    0.10
    graf
    0.10
    eted
    0.10
    itecture
    0.09
    .parametrize
    0.09
    owitz
    0.08
    ings
    0.08
    intosh
    0.08
    Activations Density 0.034%

    No Known Activations