© 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. 4175
    Prev
    Next
    INDEX
    Explanations

    references to the Protégé software used in knowledge representation and ontology development

    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
    anela
    -0.08
    ίÏĦ
    -0.07
    unker
    -0.07
    械
    -0.07
    opher
    -0.07
    ÌĤ
    -0.07
    py
    -0.07
    alement
    -0.07
    ió
    -0.07
    jab
    -0.06
    POSITIVE LOGITS
    ector
    0.09
    ocols
    0.08
    agra
    0.07
    folio
    0.06
     Wein
    0.06
     Rich
    0.06
    asio
    0.06
     prot
    0.06
     Lion
    0.06
     Prot
    0.06
    Activations Density 0.014%

    No Known Activations