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. 22-LLAMASCOPE-RES-131K
    6. 5655
    Prev
    Next
    INDEX
    Explanations

    instances of disease transmission and recovery information

    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
    202
    -0.08
     covid
    -0.07
    ccione
    -0.06
     Hydra
    -0.06
    /mp
    -0.06
    pedo
    -0.06
     Slug
    -0.06
    Äįan
    -0.06
     Psychiat
    -0.06
    ourg
    -0.06
    POSITIVE LOGITS
     Ebola
    0.10
    Dallas
    0.07
     TEX
    0.07
     Dallas
    0.07
     haz
    0.06
    oggles
    0.06
    -flight
    0.06
     isolation
    0.06
     flights
    0.06
     flown
    0.06
    Activations Density 0.004%

    No Known Activations