© 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. 105750
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to financial implications and events

    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
    оÑħ
    -0.09
    ì²Ļ
    -0.08
    ¶Į
    -0.07
    ?):
    -0.07
    ALCHEMY
    -0.07
     plá
    -0.07
     queda
    -0.07
    _escape
    -0.07
    âĹıâĹı
    -0.07
    Âłtom
    -0.07
    POSITIVE LOGITS
     .↵
    0.09
     ,
    0.09
     last
    0.08
     was
    0.08
     Âł
    0.08
     back
    0.07
    0.07
     to
    0.07
     .
    0.07
     similarly
    0.07
    Activations Density 0.048%

    No Known Activations