© 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. 16370
    Prev
    Next
    INDEX
    Explanations

    references to graphical or visual representation elements in documents

    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
    дейÑģÑĤв
    -0.07
    atars
    -0.07
    edom
    -0.06
    letal
    -0.06
    ngo
    -0.06
    éłħ
    -0.06
    oping
    -0.06
    hya
    -0.06
    eling
    -0.06
    .plist
    -0.06
    POSITIVE LOGITS
    ilogy
    0.07
    (figsize
    0.07
    .subplot
    0.07
    AllowAnonymous
    0.07
    .patch
    0.06
     Zoom
    0.06
    mag
    0.06
     Elev
    0.06
    oust
    0.06
    ResourceManager
    0.06
    Activations Density 0.002%

    No Known Activations