© 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. 72365
    Prev
    Next
    INDEX
    Explanations

    lines of code and programming constructs

    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
    etsk
    -0.08
    anik
    -0.07
    ourg
    -0.07
    vala
    -0.07
     Progressive
    -0.06
    pty
    -0.06
    оÑĢо
    -0.06
    ç¸
    -0.06
    /non
    -0.06
    egen
    -0.06
    POSITIVE LOGITS
     location
    0.07
    :CGPoint
    0.07
    iferay
    0.07
    ä½įç½®
    0.07
     distance
    0.07
     ìľĦì¹ĺ
    0.07
    =center
    0.07
     CGPointMake
    0.07
     CGPoint
    0.07
     distances
    0.07
    Activations Density 0.211%

    No Known Activations