© 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. 117916
    Prev
    Next
    INDEX
    Explanations

    references to financial investments and capital allocations

    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
    irut
    -0.07
     takdir
    -0.07
    shal
    -0.07
     اÙĦرÙħزÙĬØ©
    -0.07
    keit
    -0.07
    θη
    -0.07
    glich
    -0.07
    å½
    -0.07
    chter
    -0.07
     editable
    -0.06
    POSITIVE LOGITS
     investment
    0.13
     invest
    0.13
     investments
    0.13
     invested
    0.12
     investing
    0.11
     spend
    0.10
     Investment
    0.10
     Investments
    0.10
    invest
    0.09
     Invest
    0.09
    Activations Density 0.030%

    No Known Activations