© 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. 18027
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of being "more" or exceeding expectations

    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
    aurus
    -0.07
    âĢĮاÙĨ
    -0.06
    cury
    -0.06
    915
    -0.06
    ardi
    -0.06
    999
    -0.06
    æ¯ķ
    -0.06
    erv
    -0.06
    chwitz
    -0.06
    383
    -0.06
    POSITIVE LOGITS
     than
    0.07
     PAS
    0.07
    -than
    0.06
    enin
    0.06
    ĥģ
    0.06
    than
    0.06
    idan
    0.06
    ght
    0.06
     onStart
    0.06
     kapsamında
    0.06
    Activations Density 0.024%

    No Known Activations