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. 43662
    Prev
    Next
    INDEX
    Explanations

    expressions related to measurement or quantities

    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
     Rocky
    -0.07
     BYU
    -0.06
     Cherokee
    -0.06
     Moroccan
    -0.06
     Romans
    -0.06
     Pun
    -0.06
     Rhode
    -0.06
     Mormon
    -0.06
     Mong
    -0.05
    alon
    -0.05
    POSITIVE LOGITS
     Sistema
    0.14
     Venezuela
    0.13
     Dud
    0.13
     Venezuelan
    0.13
     El
    0.13
     Venez
    0.12
     venez
    0.12
     Venezuel
    0.12
     orchestra
    0.11
     Orchestra
    0.11
    Activations Density 0.002%

    No Known Activations