© 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. 56783
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or conditions

    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
    evi
    -0.07
    ÂĿ
    -0.07
    ntl
    -0.07
     /^[
    -0.06
    alus
    -0.06
    Äįku
    -0.06
    sov
    -0.06
    ious
    -0.06
    nings
    -0.06
    .MixedReality
    -0.06
    POSITIVE LOGITS
     whereas
    0.08
     ìĿ´ëĬĶ
    0.08
    ché
    0.07
    ÃŃg
    0.07
     which
    0.07
    ault
    0.07
     but
    0.06
     because
    0.06
     Ãľn
    0.06
     nhiên
    0.06
    Activations Density 0.036%

    No Known Activations