© 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. 121127
    Prev
    Next
    INDEX
    Explanations

    excerpts related to historical observations or descriptions of places

    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
    kowski
    -0.06
    IEEE
    -0.06
    igt
    -0.06
    ãĥ³ãĥ
    -0.06
    enberg
    -0.05
    È
    -0.05
     anesthesia
    -0.05
     shaft
    -0.05
    Binder
    -0.05
    conda
    -0.05
    POSITIVE LOGITS
    rok
    0.08
    onse
    0.08
    ãĤ±ãĥĥãĥĪ
    0.07
     treff
    0.07
    ovat
    0.07
    íݸ
    0.07
    thora
    0.07
    ινή
    0.07
    hiro
    0.07
    GRP
    0.06
    Activations Density 0.002%

    No Known Activations