© 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. 94252
    Prev
    Next
    INDEX
    Explanations

    references to various publishers, particularly Microsoft Press, and other related entities in the context of technology and information

    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
    aka
    -0.07
    iew
    -0.07
     score
    -0.06
    adoo
    -0.06
     reverse
    -0.06
    nat
    -0.06
    ity
    -0.05
    axis
    -0.05
     till
    -0.05
    bing
    -0.05
    POSITIVE LOGITS
    ²
    0.07
    ãĤīãģĽ
    0.07
    CACHE
    0.07
    /mit
    0.07
    غÙĦ
    0.07
    /Dk
    0.07
    ÎŃÏģα
    0.07
     ï¿¥
    0.07
    wdx
    0.07
    èĭ
    0.07
    Activations Density 0.004%

    No Known Activations