© 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. 17-LLAMASCOPE-RES-131K
    11. 40051
    Prev
    Next
    INDEX
    Explanations

    references to judging or evaluation processes within projects or 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
    ammer
    -0.07
    ONO
    -0.07
    алÑİ
    -0.07
    .Java
    -0.07
    rello
    -0.06
    SystemService
    -0.06
    Reporting
    -0.06
    LEGRO
    -0.06
    anian
    -0.06
    .createClass
    -0.06
    POSITIVE LOGITS
     judges
    0.11
     judge
    0.11
     panel
    0.09
     judging
    0.09
    judge
    0.08
     jury
    0.08
     votes
    0.08
     select
    0.07
    panel
    0.07
     judged
    0.07
    Activations Density 0.010%

    No Known Activations