© 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. 30038
    Prev
    Next
    INDEX
    Explanations

    words related to physical properties and characteristics of particles in a scientific context

    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
     assorted
    -0.06
    ostream
    -0.06
     alo
    -0.05
     classic
    -0.05
     Smy
    -0.05
    classic
    -0.05
     various
    -0.05
     assortment
    -0.05
    fty
    -0.05
     Ferguson
    -0.05
    POSITIVE LOGITS
    ãĤ¤ãĤ¹
    0.08
    ender
    0.08
    udit
    0.08
    endor
    0.08
    aco
    0.08
    umba
    0.08
    ÑĪев
    0.08
    ilde
    0.07
    rens
    0.07
    EndPoint
    0.07
    Activations Density 0.093%

    No Known Activations