© 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. 29078
    Prev
    Next
    INDEX
    Explanations

    references to economic measures and price controls

    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
     Millenn
    -0.07
    Tip
    -0.06
    asil
    -0.06
     Tip
    -0.06
    _supp
    -0.06
    å°ĸ
    -0.06
    intree
    -0.06
     sire
    -0.06
    wiÄħ
    -0.06
    æŃ³
    -0.06
    POSITIVE LOGITS
     oil
    0.10
     Oil
    0.09
    oil
    0.08
    Oil
    0.08
    æ²¹
    0.07
     pumping
    0.07
     output
    0.07
    æļ
    0.07
    edException
    0.06
    uder
    0.06
    Activations Density 0.003%

    No Known Activations