Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43785
    Prev
    Next
    INDEX
    Explanations

    instances of the word "even"

    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
     either
    -0.12
    either
    -0.12
     also
    -0.12
     even
    -0.11
     Either
    -0.10
    also
    -0.10
     Even
    -0.10
     Also
    -0.10
     nevertheless
    -0.10
    ä¹Łä¸į
    -0.10
    POSITIVE LOGITS
     though
    0.14
    -handed
    0.12
    though
    0.11
     worse
    0.11
    ually
    0.10
    ings
    0.10
    Though
    0.10
    ed
    0.10
    ut
    0.09
     Though
    0.09
    Activations Density 0.036%

    No Known Activations