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. 44208
    Prev
    Next
    INDEX
    Explanations

    symbols, special characters, or mathematical notation

    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
    coil
    -0.06
     Selling
    -0.06
    Visitor
    -0.06
     Aluminium
    -0.06
     Sale
    -0.05
     è¾
    -0.05
     Stocks
    -0.05
     tyre
    -0.05
    mail
    -0.05
    ¦Ĥ
    -0.05
    POSITIVE LOGITS
     riders
    0.11
     drivers
    0.11
     fares
    0.10
     rides
    0.10
     Lyft
    0.10
     rider
    0.10
     driver
    0.10
     Riders
    0.09
     ride
    0.09
    /drivers
    0.09
    Activations Density 0.003%

    No Known Activations