© 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. 59088
    Prev
    Next
    INDEX
    Explanations

    items or concepts related to technology and mobility

    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
    estruct
    -0.08
    utow
    -0.07
    dea
    -0.07
    Çİ
    -0.07
     nen
    -0.07
    .exc
    -0.07
     estruct
    -0.07
    vester
    -0.06
    .uml
    -0.06
    loor
    -0.06
    POSITIVE LOGITS
     Fulton
    0.06
    agan
    0.06
    536
    0.06
    ERG
    0.06
    è³Ģ
    0.06
     <$
    0.06
     Fle
    0.06
    िण
    0.05
     %#
    0.05
    aye
    0.05
    Activations Density 0.004%

    No Known Activations