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. 5522
    Prev
    Next
    INDEX
    Explanations

    references to regulatory bodies and legal actions involving energy companies

    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
    ARRANT
    -0.08
     ÑĢеÑģ
    -0.07
    pard
    -0.07
     Alive
    -0.07
    µ¬
    -0.07
    chal
    -0.07
    imenti
    -0.07
    ivet
    -0.07
    flight
    -0.07
     Flight
    -0.07
    POSITIVE LOGITS
     rehe
    0.09
     Commission
    0.07
    .utility
    0.07
     tariff
    0.07
    OCKET
    0.07
     utility
    0.07
     hearing
    0.07
     abandonment
    0.07
     LNG
    0.07
     gas
    0.07
    Activations Density 0.034%

    No Known Activations