© 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. 42532
    Prev
    Next
    INDEX
    Explanations

    references to crowdfunding or support for creative projects

    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
    ç§ģãģ¯
    -0.07
    ãģ£ãģ¡
    -0.07
    è¶
    -0.07
     Ñģел
    -0.06
    #+
    -0.06
    èįIJ
    -0.06
     Gallagher
    -0.06
    util
    -0.06
     verr
    -0.06
     isol
    -0.06
    POSITIVE LOGITS
     fund
    0.08
     project
    0.07
     Kickstarter
    0.07
     Extras
    0.07
     Kick
    0.07
     funding
    0.07
     Funding
    0.07
     backers
    0.06
    Kick
    0.06
     Fund
    0.06
    Activations Density 0.002%

    No Known Activations