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. 5682
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to biological processes and laboratory techniques in medical or scientific contexts

    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
    estre
    -0.08
    anou
    -0.08
    ften
    -0.07
    ilee
    -0.07
    Indented
    -0.06
    utz
    -0.06
     tin
    -0.06
    ommen
    -0.06
    åĥı
    -0.06
     surprise
    -0.06
    POSITIVE LOGITS
     previously
    0.08
     ensured
    0.07
    swith
    0.07
     kindly
    0.07
    icast
    0.07
    SFML
    0.06
     autogenerated
    0.06
     following
    0.06
    UBLIC
    0.06
    OTAL
    0.06
    Activations Density 0.147%

    No Known Activations