© 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 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. 58588
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and concepts

    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
    leh
    -0.09
    anje
    -0.07
    cctor
    -0.07
    neau
    -0.07
    &p
    -0.07
    ä¾į
    -0.07
     chod
    -0.07
    æĬŀ
    -0.07
    ernaut
    -0.07
    intree
    -0.06
    POSITIVE LOGITS
    reed
    0.07
    iat
    0.06
     же
    0.06
    orda
    0.06
    ynes
    0.05
    ebi
    0.05
    ارة
    0.05
     Sik
    0.05
     requis
    0.05
    uffman
    0.05
    Activations Density 0.000%

    No Known Activations