© 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. 75490
    Prev
    Next
    INDEX
    Explanations

    phrases related to business partnerships and collaborative efforts in technology

    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
    abant
    -0.09
    ifecycle
    -0.08
    spiel
    -0.07
    redits
    -0.07
    寿
    -0.07
    é«
    -0.07
    pyx
    -0.07
    ogany
    -0.07
    ndon
    -0.07
    roscope
    -0.07
    POSITIVE LOGITS
     mutual
    0.10
     jointly
    0.08
     respectively
    0.08
     mutually
    0.08
     together
    0.07
    ag
    0.07
    Together
    0.07
     Together
    0.06
     future
    0.06
     respective
    0.06
    Activations Density 0.025%

    No Known Activations