© 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. 116977
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "be."

    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
    æ´¥
    -0.08
     Hint
    -0.07
     maduras
    -0.07
    <small
    -0.07
    rema
    -0.06
    at
    -0.06
    kowski
    -0.06
     YÃĸ
    -0.06
    ầm
    -0.06
    strar
    -0.06
    POSITIVE LOGITS
     honest
    0.08
     frank
    0.08
     sure
    0.08
     fair
    0.08
    ланд
    0.07
    istrovstvÃŃ
    0.07
    ogle
    0.07
    à¹Ĭ
    0.07
    YRO
    0.06
    efe
    0.06
    Activations Density 0.006%

    No Known Activations