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

    Neuronpedia

    Jacobian LensNEW
    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. 78460
    Prev
    Next
    INDEX
    Explanations

    code snippets related to programming functions and error handling

    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
    enko
    -0.07
     ç¨
    -0.07
    ertools
    -0.07
    oldt
    -0.07
     vÃŃde
    -0.07
    apter
    -0.07
     /^(
    -0.07
    ourt
    -0.06
    ctor
    -0.06
     UIScreen
    -0.06
    POSITIVE LOGITS
     test
    0.10
    test
    0.08
    .test
    0.07
    teste
    0.07
    erer
    0.07
     Test
    0.07
    stub
    0.07
    Test
    0.07
    123
    0.07
     hello
    0.07
    Activations Density 0.053%

    No Known Activations