© 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. 128682
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" and related phrases concerning classification, economics, and specific nouns

    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
    -0.08
     an
    -0.08
    çļĦä¸Ģ个
    -0.07
     a
    -0.07
     itself
    -0.07
    NESS
    -0.06
    _stamp
    -0.06
    another
    -0.06
     sebuah
    -0.06
    æĺ¯ä¸Ģ个
    -0.06
    POSITIVE LOGITS
    ses
    0.14
    è¿ĻäºĽ
    0.12
    们
    0.12
    éĤ£äºĽ
    0.11
     these
    0.11
    åIJĦ
    0.11
     each
    0.11
     ê°ģ
    0.11
     respective
    0.10
    ones
    0.10
    Activations Density 0.176%

    No Known Activations