© 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. 71684
    Prev
    Next
    INDEX
    Explanations

    JavaScript events related to document readiness

    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
    unga
    -0.07
    ĵĺ
    -0.07
    DOI
    -0.06
    upal
    -0.06
    udic
    -0.06
    ileo
    -0.06
    asher
    -0.06
    unci
    -0.06
    angu
    -0.06
    ipy
    -0.06
    POSITIVE LOGITS
    лÑĥÑĩ
    0.07
    rum
    0.07
    \OptionsResolver
    0.06
    ãĤ·ãĥ¥
    0.06
     UserDao
    0.06
    beam
    0.06
     Rash
    0.06
    ante
    0.06
    ůst
    0.06
     ReactDOM
    0.06
    Activations Density 0.000%

    No Known Activations