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. 11435
    Prev
    Next
    INDEX
    Explanations

    alphanumeric characters and special symbols

    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
    ebin
    -0.07
     teammates
    -0.06
     Bedroom
    -0.06
     compan
    -0.06
    VPN
    -0.06
    vpn
    -0.05
     teammate
    -0.05
    /drivers
    -0.05
     labour
    -0.05
     VPN
    -0.05
    POSITIVE LOGITS
     museum
    0.29
     museums
    0.28
     Museum
    0.26
     Muse
    0.22
    åįļçī©
    0.22
     muse
    0.20
    useum
    0.19
     мÑĥз
    0.19
     Smithsonian
    0.15
     exhibitions
    0.14
    Activations Density 0.004%

    No Known Activations