© 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. 40829
    Prev
    Next
    INDEX
    Explanations

    punctuation related to pauses and breaks in text

    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
    ere
    -0.06
     hem
    -0.06
     неÑĹ
    -0.06
    aggi
    -0.06
    ãģ¨ãĤĤ
    -0.06
    atak
    -0.05
    æĮ¯
    -0.05
    Ñī
    -0.05
    ãģªãģĮãĤī
    -0.05
    ãĤīãģĦ
    -0.05
    POSITIVE LOGITS
    (which
    0.09
     which
    0.09
     whose
    0.09
    whose
    0.09
    which
    0.09
     WHICH
    0.08
    GLOBALS
    0.07
     Which
    0.07
     whom
    0.07
    Which
    0.07
    Activations Density 0.061%

    No Known Activations