© 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. 18724
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to scientific research, particularly in the context of networks and oscillators

    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
     multin
    -0.06
    .ud
    -0.06
    erville
    -0.06
    uesta
    -0.06
     agent
    -0.06
    umd
    -0.06
    तम
    -0.06
     enrichment
    -0.05
    Äħd
    -0.05
     Mass
    -0.05
    POSITIVE LOGITS
     EEG
    0.10
     scalp
    0.10
    Helmet
    0.08
     recordings
    0.08
    elect
    0.08
     elect
    0.08
    signals
    0.08
     signals
    0.08
     Helmet
    0.08
    coil
    0.07
    Activations Density 0.054%

    No Known Activations