© 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. 89874
    Prev
    Next
    INDEX
    Explanations

    references to quantifiable incidents or occurrences over time

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ieber
    -0.07
    .gb
    -0.07
     Sink
    -0.07
    nyder
    -0.07
    зано
    -0.07
    ä¹ħ
    -0.06
    à¹īà¸ĩ
    -0.06
    orget
    -0.06
    füh
    -0.06
    reau
    -0.06
    POSITIVE LOGITS
     alone
    0.14
     mere
    0.11
     merely
    0.11
     Alone
    0.10
     just
    0.10
     single
    0.09
    alone
    0.09
     seule
    0.09
     seul
    0.08
    mere
    0.08
    Activations Density 0.028%

    No Known Activations