© 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. 94897
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming and configuration errors

    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
    stroy
    -0.07
    sessionId
    -0.06
     spit
    -0.06
    jsonp
    -0.06
     Spit
    -0.06
    á»ijn
    -0.06
    spinner
    -0.06
    809
    -0.06
    vt
    -0.06
     exact
    -0.06
    POSITIVE LOGITS
     Arguments
    0.08
     arguments
    0.08
     declaration
    0.07
     line
    0.07
     argument
    0.07
    .syntax
    0.07
     args
    0.07
    ubs
    0.07
    ijo
    0.06
    اÛĮÙĩ
    0.06
    Activations Density 0.046%

    No Known Activations