© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 104867
    Prev
    Next
    INDEX
    Explanations

    phrases indicating opinions or viewpoints regarding various subjects

    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
    istrovstvÃŃ
    -0.06
    lico
    -0.06
     bidder
    -0.06
    ald
    -0.06
    obi
    -0.05
    aldi
    -0.05
    å®ĺ
    -0.05
    x
    -0.05
    iae
    -0.05
    umbing
    -0.05
    POSITIVE LOGITS
     regarding
    0.15
     regards
    0.15
     regard
    0.14
     concerning
    0.13
     respecto
    0.12
     Ñīодо
    0.12
    åħ³äºİ
    0.11
     vá»ģ
    0.11
     about
    0.10
    Regarding
    0.10
    Activations Density 0.029%

    No Known Activations