© 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. 117735
    Prev
    Next
    INDEX
    Explanations

    instances of the word "show" and its various forms

    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
    ãĥªãĥ³ãĤ¯
    -0.06
    ÙĩاÙĬ
    -0.06
    boo
    -0.06
    xt
    -0.06
    Dealer
    -0.06
    itter
    -0.06
    è²
    -0.06
     Dealer
    -0.06
     reason
    -0.06
    akens
    -0.06
    POSITIVE LOGITS
    yen
    0.07
    grese
    0.06
    atan
    0.06
    .localization
    0.06
    ucher
    0.06
    /testing
    0.06
    475
    0.06
    ozor
    0.06
    raith
    0.06
    hart
    0.06
    Activations Density 0.001%

    No Known Activations