© 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. 123469
    Prev
    Next
    INDEX
    Explanations

    concepts related to systems and their interactions

    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
    ä¸ĺ
    -0.07
     cmdline
    -0.07
    rig
    -0.07
    uers
    -0.06
    .Cmd
    -0.06
     srd
    -0.06
    pras
    -0.06
    insula
    -0.06
     Palette
    -0.06
    .ImageAlign
    -0.06
    POSITIVE LOGITS
     surroundings
    0.10
     environment
    0.10
    Environment
    0.09
     Environment
    0.09
    çĴ°å¢ĥ
    0.08
     interactions
    0.08
    environment
    0.08
    çݯå¢ĥ
    0.08
     environments
    0.07
     environ
    0.07
    Activations Density 0.022%

    No Known Activations