© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 42028
    Prev
    Next
    INDEX
    Explanations

    critical comparisons between different political and economic systems

    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
     itself
    -0.10
    çļĦä¸Ģ个
    -0.08
    æĺ¯ä¸Ģ个
    -0.07
    orer
    -0.07
     Böyle
    -0.07
    æĺ¯ä¸ª
    -0.07
    niest
    -0.06
    ierge
    -0.06
    ANDOM
    -0.06
    stvo
    -0.06
    POSITIVE LOGITS
     respectively
    0.40
     respective
    0.34
    åĪĨåĪ«
    0.24
     ê°ģê°ģ
    0.22
     ÑģооÑĤвеÑĤ
    0.20
    ãģĿãĤĮ
    0.17
    respect
    0.15
     alike
    0.15
     each
    0.14
     their
    0.13
    Activations Density 0.359%

    No Known Activations