© 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. 73231
    Prev
    Next
    INDEX
    Explanations

    references to actions related to change or transitions

    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
     almost
    -0.11
     nearly
    -0.09
    almost
    -0.09
     Almost
    -0.08
    Almost
    -0.08
     quite
    -0.07
     Nearly
    -0.07
     sometimes
    -0.07
     casi
    -0.06
     was
    -0.06
    POSITIVE LOGITS
     tomorrow
    0.13
     forthcoming
    0.09
     завÑĤÑĢа
    0.09
    Tomorrow
    0.09
    unlikely
    0.09
    /if
    0.08
    çļĦè¯Ŀ
    0.08
     Tomorrow
    0.08
     tonight
    0.08
     upcoming
    0.08
    Activations Density 0.048%

    No Known Activations