© 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. 28280
    Prev
    Next
    INDEX
    Explanations

    phrases related to rescue or salvation from danger

    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
    elmet
    -0.06
    беÑĢ
    -0.06
    eel
    -0.06
    alls
    -0.06
    olen
    -0.06
    icl
    -0.06
    766
    -0.06
    312
    -0.06
     soud
    -0.06
    751
    -0.06
    POSITIVE LOGITS
     khá»ıi
    0.09
    thood
    0.07
     extinction
    0.06
    ogo
    0.06
    illac
    0.06
    angkan
    0.06
     otherwise
    0.06
     Went
    0.06
    outers
    0.06
     pitch
    0.06
    Activations Density 0.009%

    No Known Activations