© 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. 15-LLAMASCOPE-RES-131K
    11. 87350
    Prev
    Next
    INDEX
    Explanations

    references to passing data or parameters in programming contexts

    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
    ilet
    -0.07
    ousse
    -0.06
    ãĥ©ãĥ³
    -0.06
    uds
    -0.06
    ial
    -0.06
     leaders
    -0.06
    ice
    -0.06
    ale
    -0.06
    erman
    -0.06
     leader
    -0.06
    POSITIVE LOGITS
     iParam
    0.07
    gfx
    0.07
    ANNEL
    0.07
     vÃło
    0.07
    robe
    0.07
    Ñĥда
    0.07
    achte
    0.07
    åĪ°
    0.06
    410
    0.06
    agrid
    0.06
    Activations Density 0.008%

    No Known Activations