© 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 EvalsExportsinterp-engineNEWAPI 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. 39263
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical activities and challenges

    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
    TEE
    -0.07
     Maiden
    -0.06
    оÑĤÑĮ
    -0.06
    /topic
    -0.06
    /local
    -0.05
    hei
    -0.05
     ı
    -0.05
    ilton
    -0.05
    earer
    -0.05
    º
    -0.05
    POSITIVE LOGITS
     ladder
    0.10
     step
    0.10
     stepped
    0.09
     stepping
    0.09
     stairs
    0.08
     climb
    0.08
    -step
    0.08
    step
    0.08
     entry
    0.08
    (step
    0.08
    Activations Density 0.028%

    No Known Activations