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. 44091
    Prev
    Next
    INDEX
    Explanations

    references to weather and physical conditions affecting events or activities

    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
    inium
    -0.07
    olis
    -0.06
    ekk
    -0.06
    arro
    -0.06
    rift
    -0.06
    rita
    -0.06
     createAction
    -0.06
    è°ĥ
    -0.06
    æĵ
    -0.06
     bekl
    -0.06
    POSITIVE LOGITS
     inc
    0.15
     pouring
    0.14
     torrent
    0.13
     adverse
    0.11
    inc
    0.11
     rainy
    0.10
     rain
    0.10
     gust
    0.10
    .inc
    0.10
     incl
    0.10
    Activations Density 0.052%

    No Known Activations