© 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. 18032
    Prev
    Next
    INDEX
    Explanations

    phrases related to returning or restoring something

    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
    esson
    -0.07
    logan
    -0.07
    Lite
    -0.07
    ı
    -0.06
    ji
    -0.06
    678
    -0.06
    think
    -0.06
     voks
    -0.06
    stadt
    -0.06
    ãĥ¼ãĥĵ
    -0.06
    POSITIVE LOGITS
     original
    0.09
     levels
    0.09
     its
    0.08
     condition
    0.07
     Levels
    0.07
     Condition
    0.07
     Its
    0.07
     originally
    0.07
     proper
    0.07
     normal
    0.06
    Activations Density 0.009%

    No Known Activations