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. 43546
    Prev
    Next
    INDEX
    Explanations

    references to physical sensations and medical conditions

    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
    Skeleton
    -0.07
    axies
    -0.07
     оÑģÑĮ
    -0.07
    èĽĽ
    -0.07
    iland
    -0.07
     Skeleton
    -0.07
     modne
    -0.07
    åde
    -0.07
    ambre
    -0.07
    oxy
    -0.07
    POSITIVE LOGITS
     tongue
    0.15
     oral
    0.14
     Oral
    0.13
     ling
    0.12
     mouth
    0.12
     tongues
    0.12
     Tong
    0.12
    èĪĮ
    0.12
     Mouth
    0.12
     taste
    0.10
    Activations Density 0.006%

    No Known Activations