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. 11540
    Prev
    Next
    INDEX
    Explanations

    mentions of international relations and defense-related activities

    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
     Hungarian
    -0.06
    ź
    -0.06
     Budapest
    -0.06
     Hungary
    -0.06
    azy
    -0.06
     СеÑĢед
    -0.06
     ÄĮech
    -0.06
     Breitbart
    -0.06
     Müz
    -0.06
     IID
    -0.06
    POSITIVE LOGITS
     Van
    0.18
     Ef
    0.15
    Van
    0.14
     Santo
    0.14
     Port
    0.12
    Ef
    0.12
     Mel
    0.11
     Ni
    0.11
     Fiji
    0.11
     Vanilla
    0.11
    Activations Density 0.006%

    No Known Activations