© 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. 117189
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental issues and controversial practices in logging

    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
    stal
    -0.07
    ansi
    -0.07
    жд
    -0.07
    linger
    -0.07
    ubyte
    -0.07
     humiliating
    -0.06
    ronics
    -0.06
    otime
    -0.06
    jedn
    -0.06
    æµ´
    -0.06
    POSITIVE LOGITS
     destruction
    0.09
     bulld
    0.09
     cutting
    0.08
     destroy
    0.08
    .Destroy
    0.08
     Destruction
    0.07
     Destroy
    0.07
     removal
    0.07
     destructive
    0.07
     destroying
    0.07
    Activations Density 0.064%

    No Known Activations