© 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. 27876
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of unraveling or revealing complex issues or emotions

    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
    edom
    -0.08
    å¾
    -0.08
    ebo
    -0.07
    lags
    -0.07
    ovice
    -0.07
     Roose
    -0.07
    że
    -0.07
    fires
    -0.07
    deme
    -0.07
    	Copyright
    -0.07
    POSITIVE LOGITS
     mysteries
    0.07
     Knot
    0.07
    线
    0.07
     linen
    0.07
    ment
    0.06
     quint
    0.06
     Myst
    0.06
     thread
    0.06
     gift
    0.06
     threads
    0.06
    Activations Density 0.006%

    No Known Activations