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. 43863
    Prev
    Next
    INDEX
    Explanations

    references to tumor-related topics and scientific measurements of tumor impacts

    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
     çķĻ
    -0.07
    usercontent
    -0.07
    داد
    -0.06
    Buzz
    -0.06
    .apple
    -0.06
    Ñģли
    -0.06
    lotte
    -0.06
    лава
    -0.06
    away
    -0.06
    éis
    -0.06
    POSITIVE LOGITS
    umor
    0.18
    issue
    0.15
    um
    0.14
    issues
    0.12
    -cell
    0.12
     Cell
    0.11
     cell
    0.10
    GF
    0.10
    ub
    0.10
    uber
    0.10
    Activations Density 0.008%

    No Known Activations