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. 11454
    Prev
    Next
    INDEX
    Explanations

    symbols or characters from various mathematical and scientific notations

    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
    Clipboard
    -0.07
    anke
    -0.07
    oola
    -0.07
    ứ
    -0.07
    atre
    -0.07
    ACHE
    -0.07
    kus
    -0.07
    ufs
    -0.07
    .echo
    -0.07
    ulle
    -0.07
    POSITIVE LOGITS
     slide
    0.10
     DAO
    0.10
     amb
    0.09
     Pic
    0.09
     frame
    0.09
     DA
    0.08
     grip
    0.08
     deco
    0.08
     polymer
    0.08
     Glock
    0.08
    Activations Density 0.004%

    No Known Activations