© 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. 2026
    Prev
    Next
    INDEX
    Explanations

    terms related to sizes, structures, and configurations in various contexts

    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
     DÄĽ
    -0.09
     Vám
    -0.08
    ｡
    -0.08
    à¹Ĩ
    -0.08
    ÚĨ
    -0.08
     ÄĮer
    -0.08
    Ìģc
    -0.07
    Äįel
    -0.07
    uhn
    -0.07
    adiens
    -0.07
    POSITIVE LOGITS
     respectively
    0.11
     alike
    0.07
     respective
    0.07
     (
    0.06
     ç¯
    0.06
    Resizable
    0.06
    ãģĿãĤĮ
    0.05
    tas
    0.05
    -plus
    0.05
     separately
    0.05
    Activations Density 0.136%

    No Known Activations