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. 5649
    Prev
    Next
    INDEX
    Explanations

    keywords related to video processing and cloud computing solutions

    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
    olumn
    -0.07
    bian
    -0.07
     mechan
    -0.07
     cazzo
    -0.06
     IGN
    -0.06
    indices
    -0.06
    ahas
    -0.06
    éĺħ读
    -0.06
     poems
    -0.06
    arf
    -0.06
    POSITIVE LOGITS
     studio
    0.08
     Studio
    0.08
     studios
    0.08
     production
    0.07
     mux
    0.07
     equipment
    0.07
     crew
    0.07
     productions
    0.07
     Production
    0.07
    Studio
    0.07
    Activations Density 0.002%

    No Known Activations