© 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. 15-LLAMASCOPE-RES-131K
    11. 520
    Prev
    Next
    INDEX
    Explanations

    references to freshwater production and environmental sustainability

    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
    illis
    -0.07
    ingham
    -0.06
     incoming
    -0.06
    ello
    -0.06
    cho
    -0.06
    noinspection
    -0.06
     ters
    -0.06
    grounds
    -0.05
     Phelps
    -0.05
    âl
    -0.05
    POSITIVE LOGITS
     formed
    0.09
    Formation
    0.08
     Formation
    0.08
    -producing
    0.08
    -production
    0.08
     formation
    0.08
    generation
    0.07
     Produced
    0.07
    formed
    0.07
     produced
    0.07
    Activations Density 0.040%

    No Known Activations