© 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. 89856
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and events

    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
    aka
    -0.06
     Stanley
    -0.06
    ìį¨
    -0.06
    æ¨
    -0.06
    ilia
    -0.06
     alike
    -0.06
    κοÏį
    -0.06
     derec
    -0.06
    ع
    -0.06
    ınca
    -0.06
    POSITIVE LOGITS
     actually
    0.14
    actually
    0.13
     nowhere
    0.10
     Actually
    0.10
     merely
    0.10
     actual
    0.09
     neither
    0.09
    Actually
    0.09
     only
    0.09
     instead
    0.09
    Activations Density 0.044%

    No Known Activations