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. 43618
    Prev
    Next
    INDEX
    Explanations

    comparative phrases that indicate an increase or emphasis in various contexts

    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
    æĽ´å¤ļ
    -0.08
     nowhere
    -0.07
    ÑģÑı
    -0.06
    obody
    -0.06
    thood
    -0.06
    imizer
    -0.06
    ixel
    -0.06
    ftime
    -0.06
     muit
    -0.06
     chưa
    -0.06
    POSITIVE LOGITS
     than
    0.16
     or
    0.14
    -or
    0.14
     like
    0.12
     of
    0.12
     akin
    0.12
     along
    0.11
    -than
    0.11
     about
    0.11
     accurately
    0.10
    Activations Density 0.035%

    No Known Activations