© 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. 27305
    Prev
    Next
    INDEX
    Explanations

    items related to programming or code elements, specifically focusing on structures and definitions

    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
    ãĥ¼ãĥ
    -0.08
    odu
    -0.07
     há»
    -0.07
    umn
    -0.07
    meler
    -0.07
    út
    -0.07
    ÄĽt
    -0.07
    meli
    -0.07
    PTR
    -0.07
    ousel
    -0.07
    POSITIVE LOGITS
    893
    0.06
     lo
    0.06
     Mane
    0.06
    889
    0.06
    å¹¹ç·ļ
    0.06
    483
    0.06
    377
    0.06
    474
    0.05
    754
    0.05
    ambi
    0.05
    Activations Density 0.008%

    No Known Activations