© 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. 54212
    Prev
    Next
    INDEX
    Explanations

    descriptions of environmental incidents and the responses to them

    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
     drown
    -0.06
    hos
    -0.06
     fict
    -0.06
    gré
    -0.06
     drowning
    -0.06
     wars
    -0.05
     rol
    -0.05
     extr
    -0.05
     Chr
    -0.05
    åłĤ
    -0.05
    POSITIVE LOGITS
    ISCO
    0.08
     slick
    0.07
     å°
    0.07
    creens
    0.07
    ắt
    0.07
    ;;;;;;;;;;;;;;;;
    0.07
    obil
    0.07
     est
    0.07
    /slick
    0.07
     oil
    0.07
    Activations Density 0.009%

    No Known Activations