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. 11495
    Prev
    Next
    INDEX
    Explanations

    references to portable power supplies and solar energy products

    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
     Slut
    -0.07
     çal
    -0.07
    .authenticate
    -0.07
    rzy
    -0.06
     Cunning
    -0.06
     muz
    -0.06
     cenu
    -0.06
     shm
    -0.06
     boÄŁ
    -0.06
     Syndrome
    -0.06
    POSITIVE LOGITS
     solar
    0.14
     Solar
    0.13
     camping
    0.12
     portable
    0.12
    Solar
    0.11
     Camping
    0.11
     Explorer
    0.11
     fold
    0.11
     Jack
    0.11
     camp
    0.11
    Activations Density 0.006%

    No Known Activations