© 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. 27148
    Prev
    Next
    INDEX
    Explanations

    numerical values and financial metrics related to socioeconomic issues

    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
     whenever
    -0.06
    ueur
    -0.06
    aklı
    -0.06
    [Boolean
    -0.06
    obel
    -0.06
    ario
    -0.06
     TMPro
    -0.06
    á»įng
    -0.06
     Ñıв
    -0.06
    akah
    -0.06
    POSITIVE LOGITS
     typical
    0.11
     Typical
    0.09
     hypothetical
    0.08
    typ
    0.08
    åħ¸
    0.07
     basic
    0.07
     Äijiá»ĥn
    0.07
     aver
    0.07
     average
    0.07
    aho
    0.07
    Activations Density 0.040%

    No Known Activations