© 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. 14442
    Prev
    Next
    INDEX
    Explanations

    innovations and advancements in technology and engineering

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    á»Ļng
    -0.07
     QuáºŃn
    -0.07
     hÃłnh
    -0.07
    ä¸Ģ级
    -0.07
     à¤Ńर
    -0.07
    gross
    -0.07
    erset
    -0.06
    (Throwable
    -0.06
    iyan
    -0.06
    ÏĢιÏĥ
    -0.06
    POSITIVE LOGITS
     technology
    0.13
     invention
    0.12
     patent
    0.12
     patented
    0.12
     technological
    0.11
    technology
    0.11
     inventions
    0.11
     Technology
    0.11
     technolog
    0.11
     patents
    0.10
    Activations Density 0.193%

    No Known Activations