© 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. 99161
    Prev
    Next
    INDEX
    Explanations

    key names and terms related to engineering and technical functions

    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
    -states
    -0.06
    abay
    -0.06
     permanently
    -0.06
     scales
    -0.06
    unity
    -0.06
    oute
    -0.06
    NDER
    -0.06
    ctor
    -0.06
    з
    -0.06
    llib
    -0.06
    POSITIVE LOGITS
    adow
    0.06
    âĸij
    0.06
    ÑĨип
    0.06
    ãĥ¼ãĥ³
    0.06
     SetLastError
    0.06
    ÄĻd
    0.06
    æĪĴ
    0.06
    codegen
    0.06
    ì©
    0.06
    margin
    0.06
    Activations Density 0.006%

    No Known Activations