© 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. 94743
    Prev
    Next
    INDEX
    Explanations

    phrases indicating instructions or actions

    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
     Canonical
    -0.07
     most
    -0.06
    etter
    -0.06
    essel
    -0.06
    et
    -0.06
     slo
    -0.06
     mo
    -0.05
    ario
    -0.05
    vc
    -0.05
    204
    -0.05
    POSITIVE LOGITS
    iaux
    0.08
    onec
    0.07
    umann
    0.07
    .MixedReality
    0.07
    idad
    0.07
    ãĥ¼ãĥį
    0.07
    .onView
    0.07
    laus
    0.07
     à¹Ĩ
    0.07
    .opensource
    0.06
    Activations Density 0.001%

    No Known Activations