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. 11490
    Prev
    Next
    INDEX
    Explanations

    references to barriers or obstacles

    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
     Cabinets
    -0.07
    pch
    -0.06
     sÃŃd
    -0.06
    imbus
    -0.06
    äºĭåĭĻ
    -0.06
    sterol
    -0.06
    för
    -0.06
    axter
    -0.06
    ìĥ
    -0.06
     Lumpur
    -0.06
    POSITIVE LOGITS
     fence
    0.14
     fencing
    0.13
     livestock
    0.12
     fences
    0.12
     electric
    0.11
     energ
    0.11
     Fence
    0.11
     pasture
    0.11
     electr
    0.11
     cattle
    0.10
    Activations Density 0.004%

    No Known Activations