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. 43499
    Prev
    Next
    INDEX
    Explanations

    concepts related to decay or deterioration

    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
    ÃŃg
    -0.06
     Blank
    -0.06
    istra
    -0.06
     Ñģлив
    -0.06
     Fauc
    -0.06
     Cassidy
    -0.06
    lectual
    -0.06
    iej
    -0.06
    PIO
    -0.06
    çķ¥
    -0.06
    POSITIVE LOGITS
     decay
    0.13
     wood
    0.13
     rot
    0.12
     timber
    0.11
     fungi
    0.11
     fungal
    0.11
     Decay
    0.10
     Wood
    0.10
    decay
    0.10
     woodworking
    0.10
    Activations Density 0.008%

    No Known Activations