© 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. 9-LLAMASCOPE-RES-131K
    11. 99100
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to signal-to-noise ratios in audio systems

    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
    EMS
    -0.06
     風
    -0.06
    ibal
    -0.06
    ual
    -0.06
     searcher
    -0.06
     extras
    -0.06
     Feast
    -0.06
    HOME
    -0.06
     alive
    -0.06
    ogl
    -0.06
    POSITIVE LOGITS
    è£ķ
    0.07
    αιο
    0.06
    ellen
    0.06
    .rc
    0.06
    viron
    0.06
    èĻij
    0.06
    /Error
    0.06
    GetObject
    0.06
    AGMA
    0.06
    rette
    0.06
    Activations Density 0.028%

    No Known Activations