© 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. 63142
    Prev
    Next
    INDEX
    Explanations

    recently occurring actions or 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
     ultimately
    -0.08
     today
    -0.08
    æľĢåĪĿ
    -0.08
     eventual
    -0.08
     originally
    -0.08
     eventually
    -0.07
     ìķĦì§ģ
    -0.07
     later
    -0.07
     earlier
    -0.07
     initially
    -0.07
    POSITIVE LOGITS
     increasingly
    0.09
     become
    0.07
     been
    0.07
     trending
    0.07
     addition
    0.07
    unto
    0.07
     mỼi
    0.07
    ecome
    0.07
    iets
    0.06
     becoming
    0.06
    Activations Density 0.038%

    No Known Activations