© 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. 16340
    Prev
    Next
    INDEX
    Explanations

    references to automotive specifications and performance features

    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
    oppable
    -0.08
    ilim
    -0.08
    ť
    -0.08
     queryInterface
    -0.07
    vrier
    -0.07
    iasm
    -0.07
    ectl
    -0.07
    ropoda
    -0.07
    ê³
    -0.07
    Ĵáŀ
    -0.07
    POSITIVE LOGITS
     increased
    0.07
     hardcore
    0.06
     beef
    0.06
     kit
    0.06
     increase
    0.06
     increases
    0.06
     rac
    0.06
     Performance
    0.06
     package
    0.06
     prof
    0.05
    Activations Density 0.008%

    No Known Activations