© 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 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. 75016
    Prev
    Next
    INDEX
    Explanations

    phrases indicating rates of change or growth

    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
    ãĥ¼ãĥ
    -0.08
    udging
    -0.07
     Mitar
    -0.07
     millennium
    -0.07
    ransition
    -0.06
     Targets
    -0.06
    aida
    -0.06
    å¨ľ
    -0.06
    InParameter
    -0.06
    anson
    -0.06
    POSITIVE LOGITS
     rate
    0.10
     rates
    0.09
    olon
    0.08
     Rate
    0.07
     faster
    0.07
    rates
    0.07
    rate
    0.07
    Rates
    0.07
     Rates
    0.07
    ret
    0.07
    Activations Density 0.008%

    No Known Activations