© 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. 77334
    Prev
    Next
    INDEX
    Explanations

    terms related to financial investments and funding

    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
    engl
    -0.07
     Toro
    -0.07
    Unified
    -0.07
    лод
    -0.07
    yonel
    -0.07
    ampo
    -0.07
    ounty
    -0.07
    vinc
    -0.07
    ê»
    -0.07
    iedad
    -0.06
    POSITIVE LOGITS
    swire
    0.06
     contributors
    0.06
     Additional
    0.06
    Ñĥв
    0.06
     previous
    0.06
     contributions
    0.06
     contribution
    0.06
     exerc
    0.06
     Previous
    0.06
    (previous
    0.06
    Activations Density 0.003%

    No Known Activations