© 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. 15518
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and function definitions

    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
    ÑĸнÑĮ
    -0.08
    rema
    -0.07
    -hide
    -0.07
     |_
    -0.07
    Markup
    -0.07
    Å¡k
    -0.07
    bum
    -0.07
     Markup
    -0.07
    REEN
    -0.07
    osto
    -0.07
    POSITIVE LOGITS
    12
    0.07
    280
    0.07
    301
    0.06
    çĪ½
    0.06
    ÑĤа
    0.06
    29
    0.06
    883
    0.06
    08
    0.06
    291
    0.06
    083
    0.06
    Activations Density 0.001%

    No Known Activations