© 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. 54363
    Prev
    Next
    INDEX
    Explanations

    specific details related to educational institutions and their locations

    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
    ัà¸ģà¸Ķ
    -0.07
    ãĥĨãĥ«
    -0.07
    ãĤ¯ãĥĪ
    -0.07
    -IN
    -0.07
    [js
    -0.06
    .bt
    -0.06
    WARE
    -0.06
    -ln
    -0.06
    ottes
    -0.06
    .easing
    -0.06
    POSITIVE LOGITS
     located
    0.09
     ợ
    0.08
     ÏĥÏĦη
    0.08
    ä½įæĸ¼
    0.08
     somewhere
    0.07
     ÏĥÏĦην
    0.07
     situated
    0.07
     near
    0.07
     elsewhere
    0.06
     Dalton
    0.06
    Activations Density 0.278%

    No Known Activations