© 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. 42609
    Prev
    Next
    INDEX
    Explanations

    terms associated with technology and innovation in various fields

    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
     respectively
    -0.07
     be
    -0.06
    asm
    -0.06
     Stam
    -0.06
     sl
    -0.05
     mid
    -0.05
    iled
    -0.05
     tort
    -0.05
    ched
    -0.05
    ä¸Ģæł·
    -0.05
    POSITIVE LOGITS
    주ëĬĶ
    0.10
    ï¼īãģ¯
    0.09
    ãģ¡ãģ¯
    0.09
    人ãģ¯
    0.09
    ìŀ¥ìĿĢ
    0.09
    )ìĿĢ
    0.08
    ìĦľëĬĶ
    0.08
    Łèĥ½
    0.08
    기ëĬĶ
    0.08
    ìĤ¬ëĬĶ
    0.08
    Activations Density 0.070%

    No Known Activations