© 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. 60729
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and relationships in technical content

    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
     opp
    -0.07
    egal
    -0.07
     âĹĦ
    -0.07
    lite
    -0.06
    ¬Ĥ
    -0.06
    0
    -0.06
    topl
    -0.05
    /op
    -0.05
    [:]
    -0.05
    igi
    -0.05
    POSITIVE LOGITS
     add
    0.08
    å¢ŀåĬł
    0.08
     union
    0.08
     Adding
    0.08
     adding
    0.08
     increased
    0.08
     UNION
    0.08
    [++
    0.08
    åIJĪ
    0.07
    å¢ŀ
    0.07
    Activations Density 0.376%

    No Known Activations