© 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. 29774
    Prev
    Next
    INDEX
    Explanations

    content related to comparisons and evaluations of models and methods in a scientific context

    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
    ongo
    -0.07
    ROC
    -0.07
    ÎŃα
    -0.07
    omu
    -0.07
    illus
    -0.07
    .scalablytyped
    -0.07
    Ł
    -0.07
    oose
    -0.07
    Lint
    -0.06
     Maze
    -0.06
    POSITIVE LOGITS
     baseline
    0.10
    baseline
    0.08
     conventional
    0.07
     traditional
    0.07
     laisse
    0.07
    aseline
    0.07
     competing
    0.07
     bas
    0.07
    sut
    0.06
    results
    0.06
    Activations Density 0.110%

    No Known Activations