© 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. 83638
    Prev
    Next
    INDEX
    Explanations

    references to external data integration needs in applications

    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
    YE
    -0.07
    ÄįnÄĽ
    -0.07
     Bek
    -0.06
    ç·ı
    -0.06
    pars
    -0.06
    /generated
    -0.06
    YLES
    -0.06
    lé
    -0.06
    /accounts
    -0.06
    祥
    -0.06
    POSITIVE LOGITS
     requirements
    0.13
     applications
    0.13
     demanding
    0.12
     requirement
    0.11
    éľĢæ±Ĥ
    0.11
     demands
    0.10
     needs
    0.10
     demand
    0.10
     Applications
    0.10
    requirements
    0.10
    Activations Density 0.107%

    No Known Activations