© 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. 15-LLAMASCOPE-RES-131K
    11. 87549
    Prev
    Next
    INDEX
    Explanations

    references to establishment or foundational actions

    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
    apolis
    -0.06
    eros
    -0.06
    i
    -0.06
    ãĤ¤ãĤ¯
    -0.06
    idea
    -0.05
    ination
    -0.05
     virgin
    -0.05
    umi
    -0.05
     square
    -0.05
    eras
    -0.05
    POSITIVE LOGITS
    ycastle
    0.08
    steel
    0.07
    èĶµ
    0.07
    zip
    0.07
     conduc
    0.07
    laughter
    0.07
    Steel
    0.07
    ingle
    0.07
    PageIndex
    0.07
    oucher
    0.07
    Activations Density 0.027%

    No Known Activations