© 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. 107735
    Prev
    Next
    INDEX
    Explanations

    keywords associated with programming constructs and APIs

    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
    RITE
    -0.07
    	Copyright
    -0.07
    {{{
    -0.06
    led
    -0.06
    çī§
    -0.06
     uncon
    -0.06
    ĽĦ
    -0.06
     erotico
    -0.06
    /layouts
    -0.06
    ÑģÑĭлки
    -0.06
    POSITIVE LOGITS
    emy
    0.07
    ieux
    0.07
    .payload
    0.06
    osy
    0.06
    kla
    0.06
    yla
    0.06
     loa
    0.06
     update
    0.06
    udded
    0.06
    azing
    0.06
    Activations Density 0.002%

    No Known Activations