© 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. 85780
    Prev
    Next
    INDEX
    Explanations

    expressions of sympathy and condolences

    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
    ondon
    -0.08
    escaping
    -0.06
    AndPassword
    -0.06
    emoc
    -0.06
    ãĥ«ãĥī
    -0.06
    ãĥ©ãĤ¹
    -0.06
    بÛĮر
    -0.06
    altar
    -0.06
    okies
    -0.06
    682
    -0.06
    POSITIVE LOGITS
    loss
    0.09
     losses
    0.08
     loss
    0.08
     Loss
    0.08
    Loss
    0.07
    -loss
    0.07
    zcze
    0.07
    ãģĹãģ®
    0.07
     ked
    0.07
    eled
    0.07
    Activations Density 0.005%

    No Known Activations