© 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. 5152
    Prev
    Next
    INDEX
    Explanations

    references to digital technology and digitalization processes

    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
    ãĥķãĤ
    -0.07
     py
    -0.07
    isclosed
    -0.06
     Fu
    -0.06
    íķĢ
    -0.06
    afort
    -0.06
    Py
    -0.06
    itesse
    -0.06
    igure
    -0.06
    mlin
    -0.06
    POSITIVE LOGITS
    åĮĸ
    0.09
    ization
    0.09
    ness
    0.08
    ification
    0.08
    ifying
    0.08
    ize
    0.07
    izing
    0.07
     revolution
    0.07
    isation
    0.07
     åĮĸ
    0.07
    Activations Density 0.053%

    No Known Activations