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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 90356
    Prev
    Next
    INDEX
    Explanations

    quantities related to U.S. dollars and financial statistics

    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
    YLE
    -0.09
    eln
    -0.07
    apos
    -0.07
    yle
    -0.07
    amide
    -0.07
    HITE
    -0.06
     MetroFramework
    -0.06
     Seal
    -0.06
     Erotik
    -0.06
    eprom
    -0.06
    POSITIVE LOGITS
     bulletin
    0.07
     critical
    0.06
    baugh
    0.06
    ugu
    0.06
    illin
    0.06
    obic
    0.06
    æħ
    0.06
    jez
    0.06
    à¸Ļà¸Ļ
    0.06
    taire
    0.06
    Activations Density 0.004%

    No Known Activations