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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 58515
    Prev
    Next
    INDEX
    Explanations

    terms related to biological diversity and classification

    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
    pose
    -0.08
    usercontent
    -0.08
    ipur
    -0.08
    à¸ī
    -0.08
    ниÑĩеÑģ
    -0.07
    åĿĬ
    -0.07
    rador
    -0.07
    etur
    -0.07
    stvÃŃ
    -0.07
    inine
    -0.07
    POSITIVE LOGITS
     species
    0.08
    aceous
    0.07
    ë¥ĺ
    0.06
    é¡ŀ
    0.06
     classes
    0.06
    -human
    0.06
     such
    0.06
     Pied
    0.06
     whose
    0.06
    noch
    0.06
    Activations Density 0.011%

    No Known Activations