© 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. 103865
    Prev
    Next
    INDEX
    Explanations

    sections of mathematical expressions or complex equations

    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
    ãĥªãĥ¼ãĤº
    -0.09
    	Copyright
    -0.09
    odore
    -0.08
    Occurred
    -0.08
    ÄĽk
    -0.07
    -grand
    -0.07
    ÃŃd
    -0.07
    ine
    -0.07
    kinson
    -0.07
    vel
    -0.07
    POSITIVE LOGITS
    forth
    0.08
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.07
    borne
    0.07
    ussen
    0.07
    tures
    0.06
    burn
    0.06
    _UNS
    0.06
    ors
    0.06
    ë¶Ħ
    0.06
    ights
    0.06
    Activations Density 0.109%

    No Known Activations