© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128739
    Prev
    Next
    INDEX
    Explanations

    elements related to enzyme development and optimization

    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
     âĵĺ
    -0.07
     Castro
    -0.07
     Pars
    -0.06
     Sloan
    -0.06
    elder
    -0.06
    hue
    -0.06
     RCS
    -0.06
    hari
    -0.06
     LTS
    -0.06
     elders
    -0.06
    POSITIVE LOGITS
    azes
    0.08
    zym
    0.08
     Attr
    0.07
     repro
    0.07
    ertas
    0.07
    ppard
    0.07
    ucid
    0.07
    ukkan
    0.07
    library
    0.07
     vign
    0.07
    Activations Density 0.021%

    No Known Activations