© 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. 1832
    Prev
    Next
    INDEX
    Explanations

    references to longstanding issues and societal themes

    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
    627
    -0.06
    λÏį
    -0.06
    zas
    -0.06
    anches
    -0.06
     ÚĨÙĪÙĨ
    -0.06
    rei
    -0.05
    .foundation
    -0.05
    787
    -0.05
    228
    -0.05
    ê
    -0.05
    POSITIVE LOGITS
     notion
    0.10
    @js
    0.07
     notions
    0.07
     totiž
    0.07
    以æĿ¥
    0.07
     tendency
    0.07
    "].(
    0.07
    --}}↵
    0.07
     saying
    0.07
    @brief
    0.07
    Activations Density 0.041%

    No Known Activations