© 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. 9-LLAMASCOPE-RES-131K
    11. 96291
    Prev
    Next
    INDEX
    Explanations

    financial figures and statistics related to monetary values

    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
    435
    -0.08
    idon
    -0.07
    quette
    -0.07
    Ïģή
    -0.07
     hod
    -0.07
     stakes
    -0.06
    ussen
    -0.06
    oret
    -0.06
    uel
    -0.06
    alı
    -0.06
    POSITIVE LOGITS
    nem
    0.07
    ATUS
    0.07
    ogh
    0.07
    erus
    0.07
    agh
    0.07
    lsa
    0.07
    ewolf
    0.06
    embre
    0.06
    ĽĦ
    0.06
     Establishment
    0.06
    Activations Density 0.028%

    No Known Activations