© 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. 96212
    Prev
    Next
    INDEX
    Explanations

    references to financial management and allocation of funds

    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
    Disposable
    -0.07
    .Dial
    -0.07
    ÐķС
    -0.06
     Genç
    -0.06
    iali
    -0.06
    ÑĤоÑĢ
    -0.06
     Dün
    -0.06
     lô
    -0.06
    azi
    -0.06
    íĶ½
    -0.06
    POSITIVE LOGITS
     directly
    0.10
     projects
    0.09
     direct
    0.09
    direct
    0.08
     Projects
    0.07
     DIRECT
    0.07
     Direct
    0.07
    Direct
    0.07
     exactly
    0.07
     areas
    0.07
    Activations Density 0.016%

    No Known Activations