© 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. 76541
    Prev
    Next
    INDEX
    Explanations

    components related to scientific methods and analysis

    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
    ajs
    -0.08
     Ekon
    -0.07
    èĶµ
    -0.07
    alon
    -0.07
    criptors
    -0.07
    guarded
    -0.07
    acters
    -0.07
    ãĤ´ãĥª
    -0.07
    ventory
    -0.07
    efa
    -0.07
    POSITIVE LOGITS
     vide
    0.07
     instructions
    0.07
     bench
    0.06
     tut
    0.06
     instruction
    0.06
     Bench
    0.06
     Lab
    0.06
     Ly
    0.06
     animal
    0.06
     postup
    0.05
    Activations Density 0.004%

    No Known Activations