© 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. 17-LLAMASCOPE-RES-131K
    11. 29573
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and valuations

    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
    ecko
    -0.08
    -scalable
    -0.08
    usta
    -0.08
    #
    -0.07
    iyan
    -0.07
    ampaign
    -0.07
    ROTO
    -0.07
    osu
    -0.07
    ICLE
    -0.07
    //{{
    -0.07
    POSITIVE LOGITS
     management
    0.06
     either
    0.06
     Bened
    0.06
     Management
    0.06
     board
    0.06
     unle
    0.06
    ither
    0.06
    ite
    0.06
     free
    0.05
     stock
    0.05
    Activations Density 0.003%

    No Known Activations