© 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 EvalsExportsAPI 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. 56100
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and thanks

    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
    hus
    -0.08
    vido
    -0.07
    ushman
    -0.07
    .scalablytyped
    -0.07
    orrent
    -0.07
    иденÑĤ
    -0.07
    mazon
    -0.07
    ieber
    -0.07
    UrlParser
    -0.07
    vÃŃc
    -0.07
    POSITIVE LOGITS
     ’
    0.07
    ale
    0.06
    achel
    0.06
    py
    0.05
     Vocal
    0.05
    ach
    0.05
     lur
    0.05
    704
    0.05
    èĶµ
    0.05
     Tim
    0.05
    Activations Density 0.007%

    No Known Activations