© 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. 62315
    Prev
    Next
    INDEX
    Explanations

    references to user input in digital forms or interfaces

    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
    vie
    -0.07
    lexport
    -0.07
    hb
    -0.07
     Writers
    -0.06
    imp
    -0.06
     Fuse
    -0.06
    ivas
    -0.06
     btnSave
    -0.06
     Lynn
    -0.06
    ê¸ī
    -0.06
    POSITIVE LOGITS
     slot
    0.06
    azzi
    0.06
     {?>↵
    0.06
     Lac
    0.06
     slots
    0.06
    ToFront
    0.06
    ieur
    0.05
    utherland
    0.05
    aptops
    0.05
    998
    0.05
    Activations Density 0.010%

    No Known Activations