© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 56747
    Prev
    Next
    INDEX
    Explanations

    conditional statements and phrases indicating conditions or requirements

    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
    lot
    -0.07
    _NAMESPACE
    -0.06
     Wass
    -0.06
    umo
    -0.06
    lein
    -0.06
     Narr
    -0.06
     Gre
    -0.06
     Moo
    -0.06
    ιÏĥÏĦο
    -0.06
     Batter
    -0.06
    POSITIVE LOGITS
    antic
    0.07
    otte
    0.07
     release
    0.07
    RELEASE
    0.07
    Ø´ÙħاÙĦÛĮ
    0.07
    ÏĢον
    0.06
    θεν
    0.06
    oxic
    0.06
     outgoing
    0.06
    Release
    0.06
    Activations Density 0.001%

    No Known Activations