© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 127252
    Prev
    Next
    INDEX
    Explanations

    phrases indicating perplexity or uncertainty regarding situations or events

    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
    stagram
    -0.07
    ãģłãģ£ãģ¦
    -0.07
    ãĤ¸ãĤ¢
    -0.07
    ernel
    -0.07
     Ùħختصات
    -0.06
    ãģĪãģ°
    -0.06
    oystick
    -0.06
    oret
    -0.06
    ála
    -0.06
    uffman
    -0.06
    POSITIVE LOGITS
     somehow
    0.20
     Somehow
    0.14
     somew
    0.12
     seems
    0.08
     apparently
    0.08
     somewhere
    0.08
     seem
    0.07
     irgend
    0.07
     manages
    0.07
     seemed
    0.07
    Activations Density 0.030%

    No Known Activations