© 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. 18120
    Prev
    Next
    INDEX
    Explanations

    attributes and characteristics of various subjects within a contextual framework

    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
     sice
    -0.09
    olicit
    -0.08
    åıĤçħ§
    -0.08
    estring
    -0.07
     btw
    -0.07
    romo
    -0.07
    ignite
    -0.07
    acin
    -0.07
    æĿŁ
    -0.07
    igh
    -0.07
    POSITIVE LOGITS
    åį´
    0.10
    åį»
    0.09
     nevertheless
    0.08
     nonetheless
    0.07
    Nevertheless
    0.07
     toch
    0.07
    ï¼Įåį´
    0.07
     still
    0.07
     nor
    0.06
     Nevertheless
    0.06
    Activations Density 0.098%

    No Known Activations