© 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 EvalsExportsAPI 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. 84205
    Prev
    Next
    INDEX
    Explanations

    terms related to gates and access systems

    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
    uxt
    -0.07
    osaur
    -0.07
    UNET
    -0.07
     Lap
    -0.07
    .streaming
    -0.06
    atri
    -0.06
     оÑĩ
    -0.06
    quet
    -0.06
    tap
    -0.06
     prem
    -0.06
    POSITIVE LOGITS
     movement
    0.10
     motion
    0.09
     mechanism
    0.09
     opener
    0.09
     opening
    0.09
    -opening
    0.08
     movements
    0.08
     mechanisms
    0.08
    opening
    0.08
    -motion
    0.08
    Activations Density 0.358%

    No Known Activations