© 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. 86042
    Prev
    Next
    INDEX
    Explanations

    the word "the."

    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
     Sunderland
    -0.07
    ÎķÎł
    -0.07
    velle
    -0.06
    undo
    -0.06
    \TestCase
    -0.06
    miss
    -0.06
    chants
    -0.06
    gress
    -0.06
    ãĥªãĤ¹
    -0.06
    ÅĽci
    -0.06
    POSITIVE LOGITS
    æ°ı
    0.06
    errer
    0.06
    emand
    0.06
    LÄ°
    0.06
     rout
    0.06
    ÅĻÃŃz
    0.06
    )frame
    0.06
     声
    0.05
    ilin
    0.05
    ÄŁinden
    0.05
    Activations Density 0.000%

    No Known Activations