© 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. 29441
    Prev
    Next
    INDEX
    Explanations

    instances of the word "when" used in various contexts

    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
     Ekon
    -0.08
    raud
    -0.08
     ayrıca
    -0.08
    ãĥªãĥ³ãĤ°
    -0.08
     ìĿ´ëŁ¬
    -0.08
    imus
    -0.08
    é¬
    -0.08
     далÑĸ
    -0.08
    egas
    -0.08
    uckle
    -0.08
    POSITIVE LOGITS
    upon
    0.09
     came
    0.07
     took
    0.07
     became
    0.07
    0.07
     during
    0.07
     showed
    0.06
     upon
    0.06
    opic
    0.06
     after
    0.06
    Activations Density 0.016%

    No Known Activations