© 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. 80230
    Prev
    Next
    INDEX
    Explanations

    phrases related to electronic systems and automation in processes

    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
     ap
    -0.06
    iras
    -0.05
     Brick
    -0.05
     brick
    -0.05
     might
    -0.05
     or
    -0.05
     prox
    -0.05
     Tester
    -0.05
     prim
    -0.05
     l
    -0.05
    POSITIVE LOGITS
    /gin
    0.09
    erin
    0.08
    /manage
    0.08
    ãĥ³ãĥIJ
    0.08
     process
    0.08
    enk
    0.07
     Process
    0.07
    ÙĩÙĨÚ¯
    0.07
     mutual
    0.07
    egan
    0.07
    Activations Density 0.011%

    No Known Activations