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. 11438
    Prev
    Next
    INDEX
    Explanations

    terms related to antibiotics

    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
    jun
    -0.07
    PLICATE
    -0.07
    achu
    -0.07
    avra
    -0.07
    stoup
    -0.07
    fork
    -0.07
    hare
    -0.07
    OSH
    -0.07
     Hab
    -0.07
    ines
    -0.07
    POSITIVE LOGITS
    acterial
    0.14
    iosis
    0.08
     microbial
    0.08
     bacterial
    0.08
     bacter
    0.07
    _ACT
    0.07
    act
    0.07
    acter
    0.07
    aterial
    0.07
    akter
    0.07
    Activations Density 0.003%

    No Known Activations