© 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. 117706
    Prev
    Next
    INDEX
    Explanations

    terms related to programming processes and functions

    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
    ,...↵↵
    -0.08
    .scalablytyped
    -0.08
    imd
    -0.08
    posta
    -0.07
    engin
    -0.07
    ÑĪки
    -0.07
    ην
    -0.07
     dve
    -0.07
    ÑŁ
    -0.07
    бÑĸ
    -0.07
    POSITIVE LOGITS
     lo
    0.07
    .newBuilder
    0.05
     mar
    0.05
    ä¸ĢæŃ¥
    0.05
     by
    0.05
     Sentinel
    0.05
     Occup
    0.05
    standen
    0.05
    AuthGuard
    0.05
    aire
    0.05
    Activations Density 0.002%

    No Known Activations