© 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. 121291
    Prev
    Next
    INDEX
    Explanations

    instances of strong sentiments or emotional expressions in the text

    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
    annis
    -0.06
    nee
    -0.06
    acho
    -0.06
    uber
    -0.06
    и
    -0.06
    olver
    -0.06
    opping
    -0.06
    ibble
    -0.06
    PRESSION
    -0.06
    åIJ
    -0.05
    POSITIVE LOGITS
    дÑĸл
    0.08
    tog
    0.07
    amac
    0.07
    ãĥ©ãĥ³ãĥī
    0.07
    DirectoryName
    0.07
    Äįen
    0.07
    olist
    0.07
    ëĵľë¦¬
    0.07
    distributed
    0.07
    Äįil
    0.06
    Activations Density 0.008%

    No Known Activations