© 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. 15-LLAMASCOPE-RES-131K
    11. 571
    Prev
    Next
    INDEX
    Explanations

    references to coding frameworks or libraries

    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
    824
    -0.06
    827
    -0.06
    ock
    -0.06
    erring
    -0.06
    casts
    -0.06
    822
    -0.06
    ignon
    -0.06
    är
    -0.05
     best
    -0.05
    ame
    -0.05
    POSITIVE LOGITS
    /../
    0.08
     anale
    0.08
    è«
    0.07
    ÃŃl
    0.07
    ãİ
    0.07
    =@"
    0.07
    åĬŁ
    0.07
    ãģ¯ãģļ
    0.07
    haft
    0.07
    ÙģتÙĩ
    0.07
    Activations Density 0.025%

    No Known Activations