© 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. 85349
    Prev
    Next
    INDEX
    Explanations

    elements related to climate change and environmental 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
    姫
    -0.07
    gebn
    -0.06
     nors
    -0.06
    .heroku
    -0.06
     Prelude
    -0.06
     UNU
    -0.06
    ег
    -0.06
    örü
    -0.06
    ]âĢı
    -0.06
    punk
    -0.06
    POSITIVE LOGITS
     Member
    0.09
     membership
    0.09
     member
    0.09
     memberships
    0.08
     Membership
    0.08
    _MEMBERS
    0.08
     lobbying
    0.08
     Members
    0.08
    Member
    0.07
     members
    0.07
    Activations Density 0.110%

    No Known Activations