© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 91801
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate timeframes or occurrences

    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
    æħ¶
    -0.07
    .nano
    -0.07
    esis
    -0.06
    obra
    -0.06
    eson
    -0.06
    jure
    -0.06
    911
    -0.06
    orns
    -0.06
    \grid
    -0.06
    ESIS
    -0.06
    POSITIVE LOGITS
    enco
    0.08
     ever
    0.08
     many
    0.07
     several
    0.07
     months
    0.07
     history
    0.06
     Months
    0.06
    ffe
    0.06
     quite
    0.06
    oras
    0.06
    Activations Density 0.009%

    No Known Activations