© 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 EvalsExportsAPI 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. 60886
    Prev
    Next
    INDEX
    Explanations

    specific details and mentions of various topics and elements within a broader context

    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
     another
    -0.10
    another
    -0.10
     otra
    -0.09
    ãģķãĤīãģ«
    -0.09
    åı¦
    -0.09
    åı¦å¤ĸ
    -0.09
    åı¦ä¸Ģ
    -0.09
     دÛĮگرÛĮ
    -0.08
     Another
    -0.08
     ãģĿãģ®ä»ĸ
    -0.08
    POSITIVE LOGITS
     first
    0.09
     earliest
    0.09
     firstly
    0.09
     Firstly
    0.08
     straightforward
    0.08
    ãģ¾ãģļ
    0.08
    à¹ģรà¸ģ
    0.08
     먼ìłĢ
    0.08
    first
    0.08
     é¦ĸ
    0.07
    Activations Density 0.077%

    No Known Activations