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. 43628
    Prev
    Next
    INDEX
    Explanations

    non-standard or special characters within the text

    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
    ši
    -0.06
    .sb
    -0.06
    gaben
    -0.06
     Ãĸr
    -0.06
    ieri
    -0.05
    ufacturer
    -0.05
     purchasing
    -0.05
     Archae
    -0.05
    .RightToLeft
    -0.05
    _macros
    -0.05
    POSITIVE LOGITS
     IPO
    0.18
     listing
    0.12
     Listing
    0.12
     listings
    0.12
    ipo
    0.10
    Listing
    0.10
    listing
    0.10
     US
    0.10
     Listings
    0.10
     listed
    0.10
    Activations Density 0.004%

    No Known Activations