© 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. 14414
    Prev
    Next
    INDEX
    Explanations

    specific terms related to financial or investment contexts

    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
    .DropDown
    -0.11
    ÛĮÙĨÙĩ
    -0.10
    _ASSUME
    -0.09
    é«
    -0.09
    //{{
    -0.09
    .yy
    -0.09
    uyla
    -0.09
    .Reporting
    -0.09
    .attachment
    -0.09
     rodin
    -0.09
    POSITIVE LOGITS
    âĢ¦↵
    0.07
    ...↵
    0.07
    ..↵
    0.06
    \-
    0.06
    ,
    0.06
    .
    0.06
     âĢ¦↵
    0.06
    Âłin
    0.06
    ↵
    0.06
    aut
    0.05
    Activations Density 0.073%

    No Known Activations