© 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. 9-LLAMASCOPE-RES-131K
    11. 94462
    Prev
    Next
    INDEX
    Explanations

    references to product series and models

    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
    ÙĪرد
    -0.06
    ÃĹ↵↵
    -0.05
    ila
    -0.05
    ãģķãģĽ
    -0.05
    anta
    -0.05
     Bacon
    -0.05
    kok
    -0.05
     mere
    -0.05
    ikh
    -0.05
    heed
    -0.05
    POSITIVE LOGITS
    ----------------------------------------------------------------------↵
    0.08
     ----------------------------------------------------------------------↵
    0.08
    odos
    0.08
     nackte
    0.07
    ìĹ´
    0.07
    .foundation
    0.07
    DMI
    0.07
    _simps
    0.07
    .xr
    0.07
    à¥ģà¤Ĥ
    0.07
    Activations Density 0.009%

    No Known Activations