© 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. 15-LLAMASCOPE-RES-131K
    11. 103624
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and scripting elements

    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
    .MixedReality
    -0.09
     createStackNavigator
    -0.08
    ãģ¨ãģĨ
    -0.08
    ÙĨدÛĮ
    -0.08
    engin
    -0.08
    íĻĶ를
    -0.08
     paci
    -0.08
     lô
    -0.08
    оÑĢе
    -0.08
     تÙĥÙĬÙĬÙģ
    -0.08
    POSITIVE LOGITS
    0.07
     (
    0.07
     /
    0.06
     cer
    0.06
    18
    0.05
     again
    0.05
    ,
    0.05
     #
    0.05
     OFF
    0.05
    .
    0.05
    Activations Density 0.033%

    No Known Activations