© 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. 41148
    Prev
    Next
    INDEX
    Explanations

    numerical values or quantities

    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
    so
    -0.06
     pulse
    -0.06
    995
    -0.06
     ens
    -0.06
    Ŀ
    -0.06
     sense
    -0.06
    rike
    -0.06
    ields
    -0.05
    PLY
    -0.05
    846
    -0.05
    POSITIVE LOGITS
    ViewItem
    0.08
    Å¡et
    0.08
     обÑĢа
    0.07
    jian
    0.07
    (strpos
    0.07
    etadata
    0.07
    راÙĤ
    0.07
    oÄŁ
    0.07
    Compact
    0.07
    ADX
    0.07
    Activations Density 0.000%

    No Known Activations