© 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. 85056
    Prev
    Next
    INDEX
    Explanations

    mentions of student engagement and academic activities

    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
    eya
    -0.08
    ptal
    -0.08
     Å¡k
    -0.08
    ucene
    -0.08
    insn
    -0.07
    adr
    -0.07
    NCY
    -0.07
    .Generated
    -0.07
    _PROGRAM
    -0.07
    ighter
    -0.07
    POSITIVE LOGITS
     essay
    0.08
     mini
    0.07
     weekly
    0.06
     Hyp
    0.06
     report
    0.06
    crit
    0.06
     yourselves
    0.06
     write
    0.06
    ene
    0.06
     cul
    0.06
    Activations Density 0.023%

    No Known Activations