© 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. 30989
    Prev
    Next
    INDEX
    Explanations

    words related to programming and software development, particularly involving IDs and function calls

    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
    een
    -0.08
    rig
    -0.07
    amine
    -0.07
    ecs
    -0.07
    ook
    -0.07
    ec
    -0.06
    ef
    -0.06
    ez
    -0.06
     Dort
    -0.06
    er
    -0.06
    POSITIVE LOGITS
    ushima
    0.07
    angelo
    0.07
    ENTITY
    0.07
    å¼ĺ
    0.07
    antro
    0.07
    имо
    0.07
    íĦ¸
    0.07
    Eval
    0.07
    ãĤ¡
    0.07
     оÑĩеÑĢед
    0.06
    Activations Density 0.010%

    No Known Activations