© 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. 73587
    Prev
    Next
    INDEX
    Explanations

    phrases related to randomized controlled trials

    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
    zza
    -0.06
     tab
    -0.06
    ue
    -0.06
    orer
    -0.05
     Comb
    -0.05
    еÑĢин
    -0.05
     Marty
    -0.05
    kla
    -0.05
    ed
    -0.05
     rak
    -0.05
    POSITIVE LOGITS
    kees
    0.08
    odesk
    0.08
    efined
    0.07
    ODE
    0.07
    -controlled
    0.07
    856
    0.07
    -Control
    0.07
     controlled
    0.07
    ause
    0.07
    -controls
    0.07
    Activations Density 0.004%

    No Known Activations