© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 60187
    Prev
    Next
    INDEX
    Explanations

    timestamps and event-related metadata

    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
    ipo
    -0.07
    -0.06
     Mur
    -0.06
    ynes
    -0.06
    iran
    -0.06
     Meals
    -0.06
    iac
    -0.06
    iola
    -0.05
    ypi
    -0.05
    ingu
    -0.05
    POSITIVE LOGITS
    ARGET
    0.08
    .neo
    0.07
    жи
    0.07
    ToLocal
    0.07
    .simps
    0.07
     mül
    0.07
    AMESPACE
    0.07
    Smarty
    0.07
    \OptionsResolver
    0.07
    983
    0.07
    Activations Density 0.002%

    No Known Activations