© 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. 108403
    Prev
    Next
    INDEX
    Explanations

    elements related to translation and authentication features in software

    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
    alars
    -0.08
     or
    -0.06
    etri
    -0.06
    ment
    -0.06
     MetroFramework
    -0.06
    slack
    -0.06
    ãģĵãģĵ
    -0.06
    alborg
    -0.06
    Overrides
    -0.06
    olle
    -0.05
    POSITIVE LOGITS
     ìĿ´ìłľ
    0.09
     ÑĤепеÑĢÑĮ
    0.08
     now
    0.08
     nynÃŃ
    0.08
     à¤ħब
    0.07
    DisplayStyle
    0.07
    now
    0.07
     RestClient
    0.07
     Previously
    0.07
     ÅŁimdi
    0.07
    Activations Density 0.003%

    No Known Activations