© 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. 14940
    Prev
    Next
    INDEX
    Explanations

    structural or formatting elements of code

    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
    rompt
    -0.07
    ädchen
    -0.07
    æĺĮ
    -0.07
    åĬŀ
    -0.06
     Fern
    -0.06
     ((__
    -0.06
    orr
    -0.06
     åĶ
    -0.06
     fewer
    -0.06
    -utils
    -0.06
    POSITIVE LOGITS
    estre
    0.07
    eh
    0.07
    licas
    0.06
    mma
    0.06
    Ŀ
    0.06
    div
    0.06
    gos
    0.06
    Ïģιν
    0.06
     Aub
    0.06
    QP
    0.06
    Activations Density 0.016%

    No Known Activations