© 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. 97316
    Prev
    Next
    INDEX
    Explanations

    numerical values and statistics

    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
    485
    -0.06
    lee
    -0.06
    uj
    -0.06
     plain
    -0.05
     stagger
    -0.05
     unlike
    -0.05
    verse
    -0.05
     for
    -0.05
    iku
    -0.05
    rost
    -0.05
    POSITIVE LOGITS
    #ad
    0.08
    jourd
    0.08
    ataire
    0.07
     arz
    0.07
    à¹Ħล
    0.07
    uyên
    0.07
    ventas
    0.07
    iage
    0.07
    	TokenName
    0.07
    nant
    0.07
    Activations Density 0.002%

    No Known Activations