© 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. 29181
    Prev
    Next
    INDEX
    Explanations

    descriptions of visual elements and imagery

    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
    tras
    -0.06
    jal
    -0.06
    ahas
    -0.06
    ched
    -0.06
    ris
    -0.06
     ch
    -0.06
     nomin
    -0.06
     Buckley
    -0.06
    ople
    -0.05
    æ¸Ī
    -0.05
    POSITIVE LOGITS
     belong
    0.09
     belonged
    0.09
    æĺ¯æĪij
    0.09
     belongs
    0.08
    ìŀ¥ìĿĢ
    0.08
     represent
    0.08
    çļĦæĺ¯
    0.08
    ìŀIJëĬĶ
    0.08
     reflect
    0.08
     adalah
    0.07
    Activations Density 0.104%

    No Known Activations