© 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. 4752
    Prev
    Next
    INDEX
    Explanations

    phrases related to troubleshooting and updating digital content

    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
    agues
    -0.06
    ir
    -0.06
     Marshall
    -0.06
     Tun
    -0.05
    ág
    -0.05
     Tib
    -0.05
    arters
    -0.05
    hab
    -0.05
     covers
    -0.05
    ana
    -0.05
    POSITIVE LOGITS
    istrovstvÃŃ
    0.10
    ¶ģ
    0.08
    Fcn
    0.08
     kì
    0.08
    /REC
    0.07
    ĮĴ
    0.07
    NotificationCenter
    0.07
    ADX
    0.07
    «ĺ
    0.07
    paque
    0.07
    Activations Density 0.028%

    No Known Activations