© 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. 104841
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or events that occur after a certain condition or point in time

    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
    lich
    -0.08
    igure
    -0.08
    bout
    -0.07
    gi
    -0.07
    iso
    -0.07
    нимаеÑĤ
    -0.07
    δει
    -0.07
    _DS
    -0.07
    одеÑĢж
    -0.06
     Merk
    -0.06
    POSITIVE LOGITS
     already
    0.12
    already
    0.09
    å·²ç»ı
    0.07
    Already
    0.07
     initial
    0.07
     Already
    0.07
     Ñĥже
    0.07
    ãĥ³ãĥ
    0.07
     już
    0.07
     established
    0.07
    Activations Density 0.021%

    No Known Activations