© 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. 3599
    Prev
    Next
    INDEX
    Explanations

    descriptions of quality or purity in experiences, products, or narratives

    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
    .views
    -0.07
    à¸Ĺาà¸ĩ
    -0.06
    ãĥ³ãĥij
    -0.06
    à¹Īาà¸ģ
    -0.06
    pong
    -0.06
    Ư
    -0.06
     Cleans
    -0.06
    orama
    -0.06
    /cs
    -0.06
    λÏī
    -0.06
    POSITIVE LOGITS
     sheer
    0.08
     pure
    0.07
    foy
    0.07
    .githubusercontent
    0.07
     Wild
    0.07
    ley
    0.07
    ingly
    0.07
    edly
    0.07
     Bakan
    0.06
    -ÑĤаки
    0.06
    Activations Density 0.006%

    No Known Activations