© 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. 40565
    Prev
    Next
    INDEX
    Explanations

    mentions of scientific journals and related research topics

    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
    launcher
    -0.07
    ÏĢει
    -0.06
    ÑĴ
    -0.06
    utsch
    -0.06
    .FONT
    -0.06
    emony
    -0.06
    ãĥĨãĥ«
    -0.06
    ombres
    -0.06
    ÑĪÑĤ
    -0.06
    te
    -0.06
    POSITIVE LOGITS
    261
    0.08
     foreground
    0.06
    413
    0.06
    894
    0.06
    unde
    0.06
    674
    0.06
    327
    0.06
    562
    0.06
    704
    0.06
    icare
    0.06
    Activations Density 0.001%

    No Known Activations