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

    Neuronpedia

    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. 22-LLAMASCOPE-RES-131K
    11. 3967
    Prev
    Next
    INDEX
    Explanations

    terms related to climate modeling and environmental data analysis

    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
    ÑĢоÑģ
    -0.06
     miscellaneous
    -0.06
    upal
    -0.06
     rarity
    -0.06
     simp
    -0.05
    alta
    -0.05
    nia
    -0.05
    perc
    -0.05
     analyzer
    -0.05
    ophon
    -0.05
    POSITIVE LOGITS
     products
    0.08
    erdale
    0.08
     Ensemble
    0.08
    ppv
    0.07
    products
    0.07
    -ahead
    0.07
    ensemble
    0.07
     Sản
    0.07
    ertino
    0.07
    userinfo
    0.07
    Activations Density 0.031%

    No Known Activations