© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 91787
    Prev
    Next
    INDEX
    Explanations

    references to renewable energy and its benefits

    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
     breath
    -0.07
    amon
    -0.07
    ÙĨج
    -0.06
     syn
    -0.06
    _PORTS
    -0.06
    enses
    -0.06
     acceler
    -0.06
     Catal
    -0.06
    ãĥ¼ãĥĭ
    -0.06
     compartment
    -0.06
    POSITIVE LOGITS
     power
    0.09
     generation
    0.09
     Output
    0.08
     output
    0.07
    power
    0.07
    generation
    0.07
    _generation
    0.07
     outputs
    0.07
    .generated
    0.07
    output
    0.07
    Activations Density 0.010%

    No Known Activations