© 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. 95324
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the start of a correspondence or communication

    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
    ims
    -0.07
    avel
    -0.07
    een
    -0.07
    bart
    -0.06
    aring
    -0.06
    earing
    -0.06
    ovan
    -0.06
    ze
    -0.06
    ARING
    -0.06
    upert
    -0.06
    POSITIVE LOGITS
    Argb
    0.09
    antis
    0.09
    دÙĪاج
    0.08
    cak
    0.08
    Å¡ker
    0.07
    dee
    0.07
     left
    0.07
    _STMT
    0.07
    hoff
    0.07
    grese
    0.07
    Activations Density 0.013%

    No Known Activations