© 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. 17-LLAMASCOPE-RES-131K
    11. 107269
    Prev
    Next
    INDEX
    Explanations

    instances of significant numerical data

    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
     loose
    -0.06
    aneous
    -0.06
     til
    -0.06
    -most
    -0.06
    ücü
    -0.06
    posix
    -0.05
    amus
    -0.05
    cast
    -0.05
    plor
    -0.05
     ot
    -0.05
    POSITIVE LOGITS
    ipel
    0.07
     serm
    0.07
    DEX
    0.07
    erti
    0.07
    urger
    0.07
    aterangepicker
    0.07
    duck
    0.07
    REFIX
    0.07
     ima
    0.07
    AYOUT
    0.06
    Activations Density 0.000%

    No Known Activations