© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 55059
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial investment 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
    agra
    -0.08
     اÙĦرÙħزÙĬØ©
    -0.07
    Ĭ¶
    -0.07
    ucked
    -0.07
    stateParams
    -0.07
    kh
    -0.07
    voke
    -0.07
    ksam
    -0.06
     Kral
    -0.06
    efe
    -0.06
    POSITIVE LOGITS
     growth
    0.09
     expansion
    0.08
     further
    0.08
     Expansion
    0.07
     immediate
    0.06
     Growth
    0.06
     continued
    0.06
    Expansion
    0.06
     continue
    0.06
    icable
    0.06
    Activations Density 0.006%

    No Known Activations