© 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. 73190
    Prev
    Next
    INDEX
    Explanations

    references to mortality and ethical behavior

    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
    ylon
    -0.07
    hti
    -0.07
    /pkg
    -0.06
     Weather
    -0.06
    obl
    -0.06
    ære
    -0.06
    apur
    -0.06
    ÅĤem
    -0.06
     Tehran
    -0.06
    ÅĤu
    -0.06
    POSITIVE LOGITS
    erdale
    0.07
     Hindered
    0.07
    nz
    0.07
    γο
    0.07
    ROWSER
    0.07
    duct
    0.07
    ContextHolder
    0.07
    ÏĦÏĮ
    0.06
    ayout
    0.06
     yourselves
    0.06
    Activations Density 0.001%

    No Known Activations