© 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. 124599
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, organizations, or events

    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
    anders
    -0.07
    ials
    -0.07
    ELLOW
    -0.07
    ertz
    -0.06
    'Ñı
    -0.06
    orget
    -0.06
     eg
    -0.06
    eg
    -0.06
    orado
    -0.06
    æģĴ
    -0.06
    POSITIVE LOGITS
     compared
    0.09
     whereas
    0.07
    adero
    0.07
    igu
    0.07
     alone
    0.07
     Contrast
    0.07
    रण
    0.07
     плÑİ
    0.07
    iloc
    0.07
    ;line
    0.06
    Activations Density 0.086%

    No Known Activations