© 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. 60994
    Prev
    Next
    INDEX
    Explanations

    concepts related to financial development and investment 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
    akash
    -0.06
    pong
    -0.06
    ABA
    -0.06
    FLASH
    -0.06
     Gala
    -0.06
    cas
    -0.05
    åIJ
    -0.05
    ué
    -0.05
    gap
    -0.05
    annel
    -0.05
    POSITIVE LOGITS
    aut
    0.07
    Це
    0.07
    ÑģÑĮ
    0.07
    驾
    0.06
     Thanh
    0.06
    ì°¬
    0.06
    plete
    0.06
    ibble
    0.06
     YYS
    0.06
    ervlet
    0.06
    Activations Density 0.020%

    No Known Activations