© 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 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. 59191
    Prev
    Next
    INDEX
    Explanations

    references to data extraction and synchronization processes

    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
    elez
    -0.07
     migrationBuilder
    -0.07
    elas
    -0.07
    kov
    -0.07
    å°¾
    -0.07
    ellas
    -0.07
    odi
    -0.06
    eland
    -0.06
    stantiate
    -0.06
     Muk
    -0.06
    POSITIVE LOGITS
     update
    0.12
     updates
    0.11
    updates
    0.10
    update
    0.10
     updating
    0.10
     Update
    0.09
     refresh
    0.09
     refreshing
    0.09
    _update
    0.09
     Updates
    0.09
    Activations Density 0.101%

    No Known Activations