© 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. 60895
    Prev
    Next
    INDEX
    Explanations

    phrases related to durations and 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
    ož
    -0.08
     pret
    -0.07
    oa
    -0.06
    à¥ĩष
    -0.06
     pretext
    -0.06
    .library
    -0.06
    PEAR
    -0.06
     gó
    -0.06
    insky
    -0.06
    LLU
    -0.06
    POSITIVE LOGITS
    ewolf
    0.07
     nữa
    0.06
    ifiable
    0.06
    otto
    0.06
    -average
    0.06
    ckett
    0.06
    âĢį
    0.06
     sayıda
    0.06
    eful
    0.06
    ekim
    0.06
    Activations Density 0.009%

    No Known Activations