© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 88068
    Prev
    Next
    INDEX
    Explanations

    comparative phrases related to performance and efficiency

    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
    ereg
    -0.06
    _performance
    -0.06
    mare
    -0.06
    amba
    -0.06
    INGTON
    -0.06
    cen
    -0.06
    ibold
    -0.06
    educt
    -0.06
    ayne
    -0.06
    esen
    -0.06
    POSITIVE LOGITS
     safety
    0.08
     Safety
    0.07
     Safe
    0.07
    yonel
    0.07
    å®īåħ¨
    0.07
     surviv
    0.06
    خاÙĨÙĩ
    0.06
    Safety
    0.06
    -safe
    0.06
    iage
    0.06
    Activations Density 0.061%

    No Known Activations