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. 43458
    Prev
    Next
    INDEX
    Explanations

    numerical values and specific days of the week

    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
    Fri
    -0.14
     Fri
    -0.14
     Weekend
    -0.12
     weekend
    -0.12
     mono
    -0.11
     weekends
    -0.11
     fri
    -0.11
    Sat
    -0.10
    mono
    -0.10
    omon
    -0.10
    POSITIVE LOGITS
     Wednesday
    0.33
    Wednesday
    0.29
     Wed
    0.28
     wed
    0.24
    Wed
    0.21
     wedge
    0.19
    wed
    0.19
    17
    0.13
     Tuesday
    0.13
     Wend
    0.12
    Activations Density 0.015%

    No Known Activations