© 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. 82034
    Prev
    Next
    INDEX
    Explanations

    adjectives and terms related to specialized fields 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
    es
    -0.15
    ed
    -0.11
    eses
    -0.10
    et
    -0.10
    edb
    -0.09
    em
    -0.09
    e
    -0.09
    ech
    -0.09
    esen
    -0.09
    ee
    -0.09
    POSITIVE LOGITS
    ism
    0.16
    ized
    0.16
    ists
    0.15
    dehyde
    0.14
    ities
    0.14
    ize
    0.14
    izing
    0.14
    ised
    0.13
    mente
    0.12
    ising
    0.12
    Activations Density 0.080%

    No Known Activations