© 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. 27360
    Prev
    Next
    INDEX
    Explanations

    references to technological advancements and specific systems or devices

    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
    707
    -0.07
    ï¿
    -0.06
    .dense
    -0.06
     rarely
    -0.06
     Wid
    -0.06
     opioids
    -0.05
     widely
    -0.05
    .scalablytyped
    -0.05
    \:
    -0.05
    uster
    -0.05
    POSITIVE LOGITS
    ampo
    0.08
    enia
    0.08
    Åĵur
    0.08
    Compatibility
    0.07
    prech
    0.07
     æĬ
    0.07
    sWith
    0.07
    ason
    0.07
    ipo
    0.07
    affected
    0.07
    Activations Density 0.064%

    No Known Activations