© 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 EvalsExportsinterp-engineNEWAPI 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. 4549
    Prev
    Next
    INDEX
    Explanations

    terms related to sustainability in various 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
    åŁ
    -0.08
    práv
    -0.06
    ou
    -0.06
    agle
    -0.06
    ëĿ½
    -0.06
     Powers
    -0.06
    955
    -0.06
    Ìĥ
    -0.06
    ond
    -0.06
    FontAwesome
    -0.06
    POSITIVE LOGITS
    ably
    0.09
    licken
    0.07
     solutions
    0.07
    éºĹ
    0.07
     solution
    0.07
    ekim
    0.07
    tach
    0.07
     future
    0.06
    ardown
    0.06
     Goldberg
    0.06
    Activations Density 0.010%

    No Known Activations