© 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. 61554
    Prev
    Next
    INDEX
    Explanations

    references to industrial processes related to iron and steel production

    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
    kate
    -0.07
    adesh
    -0.07
     Grill
    -0.06
    eneg
    -0.06
    åĻ¨
    -0.06
     eater
    -0.06
    Unnamed
    -0.06
    isse
    -0.06
     sess
    -0.06
    kah
    -0.06
    POSITIVE LOGITS
     sale
    0.07
    973
    0.07
    زا
    0.07
     accom
    0.06
    IGHLIGHT
    0.06
    alie
    0.06
    lobals
    0.06
    ko
    0.06
    ัà¹Ī
    0.06
     krev
    0.06
    Activations Density 0.005%

    No Known Activations