© 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. 121520
    Prev
    Next
    INDEX
    Explanations

    expressions of approval or positive sentiments

    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
    asthan
    -0.07
    IClient
    -0.07
    ubat
    -0.06
    ivia
    -0.06
     massaggi
    -0.06
     wink
    -0.06
    owie
    -0.06
     Gaw
    -0.06
    olver
    -0.06
    Advertising
    -0.06
    POSITIVE LOGITS
    WARD
    0.06
    ward
    0.06
    ople
    0.06
    atisf
    0.06
    ipa
    0.06
     discontin
    0.06
     satisf
    0.06
    eya
    0.05
     Nets
    0.05
    ebra
    0.05
    Activations Density 0.000%

    No Known Activations