© 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. 73907
    Prev
    Next
    INDEX
    Explanations

    phrases related to software comparisons and versions

    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
    inch
    -0.07
    ka
    -0.06
    à¹ģà¸ļà¸ļ
    -0.06
     mono
    -0.06
     rarity
    -0.06
     Bias
    -0.06
     bias
    -0.06
    bek
    -0.06
    ëĬ¥
    -0.05
    mdir
    -0.05
    POSITIVE LOGITS
     differences
    0.09
     features
    0.09
     Differences
    0.09
     Features
    0.08
     certain
    0.08
    å·®
    0.08
     оÑģновнÑĭÑħ
    0.07
     项
    0.07
     elements
    0.07
     Difference
    0.07
    Activations Density 0.037%

    No Known Activations