© 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. 40574
    Prev
    Next
    INDEX
    Explanations

    references to automotive performance and specifications

    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
    éra
    -0.07
     Sham
    -0.07
    lam
    -0.07
    ég
    -0.07
    еди
    -0.06
    abi
    -0.06
    -dat
    -0.06
     begr
    -0.06
    ussy
    -0.06
     èĩªåĬ¨çĶŁæĪIJ
    -0.06
    POSITIVE LOGITS
    ãĤº
    0.07
    cea
    0.07
    adele
    0.06
    iler
    0.06
     Sistem
    0.06
     Verde
    0.06
    aza
    0.06
    uman
    0.06
    Neighbor
    0.06
     premise
    0.06
    Activations Density 0.002%

    No Known Activations