© 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. 5430
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to sequences and their properties

    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
    /loose
    -0.08
    æ²»
    -0.07
    icros
    -0.07
    ίÏĥ
    -0.06
     ($)
    -0.06
     darm
    -0.06
    ahn
    -0.06
     Hlav
    -0.06
    (\$
    -0.06
    ίνα
    -0.06
    POSITIVE LOGITS
    adier
    0.06
     اÙĦØ£ÙĨ
    0.06
    osi
    0.06
    ephir
    0.06
    sert
    0.06
     Wire
    0.06
    ÑĪиÑģÑĮ
    0.06
     Hemp
    0.06
     irgend
    0.06
    shift
    0.06
    Activations Density 0.054%

    No Known Activations