© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 128547
    Prev
    Next
    INDEX
    Explanations

    scientific references and data related to enzyme classification and biochemical studies

    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
     Springer
    -0.08
    hta
    -0.07
    åĩ¡
    -0.07
    ATAR
    -0.07
     Tham
    -0.07
    rys
    -0.07
    oldem
    -0.06
    eza
    -0.06
    ortex
    -0.06
     Overs
    -0.06
    POSITIVE LOGITS
    171
    0.06
     вип
    0.06
    227
    0.06
     Front
    0.06
    Front
    0.06
    singleton
    0.06
     impro
    0.06
    175
    0.06
    ue
    0.06
     LORD
    0.06
    Activations Density 0.022%

    No Known Activations