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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 129103
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to geometry and data structures

    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
     ultimo
    -0.08
    .Last
    -0.07
     LAST
    -0.07
    Lastly
    -0.07
    LAST
    -0.07
    olang
    -0.07
    æľĢå¾Į
    -0.07
     dern
    -0.07
    ãĤĤãģĨ
    -0.07
     Lastly
    -0.07
    POSITIVE LOGITS
     first
    0.26
    first
    0.21
    第ä¸Ģ
    0.19
     pierws
    0.18
     첫
    0.17
    .first
    0.17
     primero
    0.17
    _first
    0.16
     eerste
    0.16
     prvnÃŃ
    0.16
    Activations Density 0.400%

    No Known Activations