© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14222
    Prev
    Next
    INDEX
    Explanations

    details related to financial transactions and corporate acquisitions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ãģ®ãĤĪãģĨãģ«
    -0.07
    anyahu
    -0.07
    ÏĥÏĢ
    -0.07
    odesk
    -0.07
    evin
    -0.06
    ifest
    -0.06
    appa
    -0.06
    reat
    -0.06
    ναÏĤ
    -0.06
     меÑĤалли
    -0.06
    POSITIVE LOGITS
     terms
    0.08
     deal
    0.07
    Terms
    0.07
     Terms
    0.07
    olin
    0.06
     transaction
    0.06
     exact
    0.06
     news
    0.06
     Neither
    0.06
     Both
    0.06
    Activations Density 0.016%

    No Known Activations