© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 60363
    Prev
    Next
    INDEX
    Explanations

    phrases about growth and support for local businesses or communities

    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
    amet
    -0.08
    steller
    -0.07
    aida
    -0.07
    NCY
    -0.07
    aille
    -0.07
     ÑĪлÑıÑħом
    -0.07
    eyin
    -0.07
    ovsky
    -0.06
    erdale
    -0.06
    herits
    -0.06
    POSITIVE LOGITS
    /or
    0.07
    rog
    0.06
     QC
    0.06
    ret
    0.06
     indeed
    0.05
     Policies
    0.05
    ata
    0.05
    ãģĭãĤĬ
    0.05
    rets
    0.05
     Babies
    0.05
    Activations Density 0.035%

    No Known Activations