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. 43774
    Prev
    Next
    INDEX
    Explanations

    references to fake news and disinformation

    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
    é¢Ħè§Ī
    -0.06
    LOPT
    -0.06
     Preview
    -0.06
    ictor
    -0.06
    gett
    -0.05
    اÙģØª
    -0.05
    _preview
    -0.05
    ricular
    -0.05
     Synopsis
    -0.05
    ottie
    -0.05
    POSITIVE LOGITS
     spreading
    0.13
     circulating
    0.12
     spread
    0.12
     disse
    0.12
     circulated
    0.11
     misinformation
    0.11
     circulation
    0.11
     online
    0.10
     dissemination
    0.10
     spreads
    0.10
    Activations Density 0.039%

    No Known Activations