© 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. 28998
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific and technical concepts

    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
    cott
    -0.07
    erness
    -0.06
     thức
    -0.06
     Pepper
    -0.06
    ucken
    -0.06
    irl
    -0.06
     Nex
    -0.06
    èĢħçļĦ
    -0.06
    jr
    -0.06
     comp
    -0.06
    POSITIVE LOGITS
    /Internal
    0.09
     ex
    0.09
    remely
    0.09
    /import
    0.08
    (EX
    0.08
    ansion
    0.08
    OVÃģ
    0.08
    uber
    0.07
    mpl
    0.07
    unge
    0.07
    Activations Density 0.052%

    No Known Activations