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. 5714
    Prev
    Next
    INDEX
    Explanations

    LaTeX command structures and formatting elements

    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
    ák
    -0.06
    ooth
    -0.06
     coli
    -0.06
     depress
    -0.06
    ereg
    -0.06
     Market
    -0.05
    _cast
    -0.05
    çij
    -0.05
    ÃŃd
    -0.05
    .market
    -0.05
    POSITIVE LOGITS
    imed
    0.07
    yer
    0.07
    ë§ī
    0.07
    .asc
    0.06
    ako
    0.06
    ownt
    0.06
    istrat
    0.06
    hire
    0.06
    tons
    0.06
    .Chrome
    0.06
    Activations Density 0.069%

    No Known Activations