© 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. 94310
    Prev
    Next
    INDEX
    Explanations

    references to generational characteristics and comparisons

    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
    byss
    -0.07
    IfExists
    -0.07
    .myapplication
    -0.07
    coop
    -0.07
    yne
    -0.07
     ì¡
    -0.07
    ighton
    -0.07
    semb
    -0.07
    amedi
    -0.07
    sse
    -0.07
    POSITIVE LOGITS
     decade
    0.06
    inement
    0.06
     everything
    0.06
    /misc
    0.06
    IDS
    0.06
     things
    0.06
     Jude
    0.06
     maybe
    0.06
     after
    0.06
    indsight
    0.05
    Activations Density 0.006%

    No Known Activations