© 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. 55560
    Prev
    Next
    INDEX
    Explanations

    phrases and descriptions related to size, weight, and challenges associated with transporting items

    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
    blink
    -0.07
    ade
    -0.07
    toFloat
    -0.07
     Unt
    -0.07
     reservoir
    -0.06
    outh
    -0.06
     Floating
    -0.06
    elson
    -0.06
    unt
    -0.06
    åľĪ
    -0.06
    POSITIVE LOGITS
     bulky
    0.10
    size
    0.09
     Size
    0.09
     size
    0.09
     volume
    0.09
    -size
    0.08
    )size
    0.08
     sizes
    0.08
     Dimensions
    0.08
    -volume
    0.08
    Activations Density 0.016%

    No Known Activations