© 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. 4574
    Prev
    Next
    INDEX
    Explanations

    phrases related to energy and climate policy initiatives

    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
    arya
    -0.08
    gth
    -0.07
     Vive
    -0.07
     Cow
    -0.07
    (Current
    -0.07
    hek
    -0.07
    rede
    -0.07
    akest
    -0.07
    YNAM
    -0.06
    ıs
    -0.06
    POSITIVE LOGITS
     increasingly
    0.07
     reliance
    0.07
    agens
    0.07
     amore
    0.07
    aged
    0.07
    ihar
    0.06
     more
    0.06
     towards
    0.06
     toward
    0.06
    addtogroup
    0.06
    Activations Density 0.015%

    No Known Activations