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. 22-LLAMASCOPE-RES-131K
    6. 5699
    Prev
    Next
    INDEX
    Explanations

    references to user or customer interactions and roles within a system

    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
    iras
    -0.07
     Gors
    -0.06
    SURE
    -0.06
    wal
    -0.06
    BF
    -0.06
     survivor
    -0.06
     sympathy
    -0.06
     eof
    -0.06
     ÙģØ§Ø±
    -0.06
    /fwlink
    -0.06
    POSITIVE LOGITS
     simply
    0.10
     no
    0.09
     simplement
    0.08
     merely
    0.08
     benefit
    0.08
     artık
    0.08
     benefits
    0.08
     Simply
    0.08
    Simply
    0.07
    Receive
    0.07
    Activations Density 0.035%

    No Known Activations