© 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. 77199
    Prev
    Next
    INDEX
    Explanations

    references to legislative bills and their statuses

    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
    abad
    -0.07
    áno
    -0.07
     settles
    -0.06
    lev
    -0.06
    .
    -0.06
     inward
    -0.06
     settling
    -0.06
     storefront
    -0.06
     cling
    -0.05
     settle
    -0.05
    POSITIVE LOGITS
     passed
    0.10
    passed
    0.08
     bill
    0.08
    addtogroup
    0.08
    -pass
    0.07
    zilla
    0.07
    Passed
    0.07
     passage
    0.07
     Passed
    0.07
    çĦ¦
    0.07
    Activations Density 0.027%

    No Known Activations