© 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. 123943
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate promptness or urgency in actions or procedures

    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
    alian
    -0.07
    wend
    -0.06
    volatile
    -0.06
    okoj
    -0.06
     bri
    -0.06
    sworth
    -0.06
    åīįçļĦ
    -0.06
    \widgets
    -0.06
    increment
    -0.06
    寿
    -0.06
    POSITIVE LOGITS
     manner
    0.11
     fashion
    0.08
    xffffffff
    0.07
     Fashion
    0.07
     Carpenter
    0.07
     manners
    0.07
     time
    0.06
    ece
    0.06
    Fashion
    0.06
    á»ijc
    0.06
    Activations Density 0.002%

    No Known Activations