© 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 EvalsExportsinterp-engineNEWAPI 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. 61126
    Prev
    Next
    INDEX
    Explanations

    programming syntax and control structures

    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
     Eig
    -0.07
    arel
    -0.06
    æ³ī
    -0.06
    Streams
    -0.06
    ãģĴ
    -0.06
    using
    -0.06
    ,LOCATION
    -0.06
    ÅĻeh
    -0.06
     Geological
    -0.06
    &e
    -0.06
    POSITIVE LOGITS
    807
    0.06
    819
    0.06
    dbo
    0.06
    537
    0.06
    à¸Ļะ
    0.06
    818
    0.06
    eking
    0.06
    RIA
    0.06
    820
    0.05
    GIN
    0.05
    Activations Density 0.136%

    No Known Activations