© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 61294
    Prev
    Next
    INDEX
    Explanations

    concepts related to improving models and their performance metrics in machine learning

    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
    modification
    -0.06
     bis
    -0.06
     EX
    -0.06
     Verfüg
    -0.06
    rak
    -0.06
     Proud
    -0.06
     pitching
    -0.06
    modify
    -0.06
    serie
    -0.06
    modifiable
    -0.05
    POSITIVE LOGITS
     performance
    0.10
     performances
    0.09
     overall
    0.09
    performance
    0.08
    igham
    0.08
    åª
    0.07
    ulin
    0.07
    æĢ§èĥ½
    0.07
     results
    0.07
    FLAG
    0.07
    Activations Density 0.068%

    No Known Activations