© 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. 84105
    Prev
    Next
    INDEX
    Explanations

    references to corporate investments and growth strategies

    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
    prm
    -0.08
    é»İ
    -0.07
    stub
    -0.07
     zel
    -0.07
     kino
    -0.07
    ÏĦον
    -0.07
    веÑī
    -0.06
     mev
    -0.06
    crm
    -0.06
     ún
    -0.06
    POSITIVE LOGITS
     plant
    0.09
     Plant
    0.08
    plant
    0.07
     plants
    0.07
     facility
    0.07
     Plants
    0.07
    YLES
    0.07
     Customers
    0.07
    Plant
    0.07
    ded
    0.06
    Activations Density 0.012%

    No Known Activations