© 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. 62768
    Prev
    Next
    INDEX
    Explanations

    topics related to cleaning and maintaining products, particularly plastics and leather

    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
    åĪĩãĤĬ
    -0.07
    osy
    -0.07
    dj
    -0.06
    ÅĻÃŃž
    -0.06
    аÑĢÑĩ
    -0.06
    esk
    -0.06
    ppelin
    -0.06
    anium
    -0.06
    ymes
    -0.06
    iences
    -0.06
    POSITIVE LOGITS
     surfaces
    0.08
     streak
    0.08
     car
    0.08
     rep
    0.08
     buff
    0.07
     surface
    0.07
     finish
    0.07
     rub
    0.07
     rubbed
    0.07
     gloss
    0.07
    Activations Density 0.017%

    No Known Activations