Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40480
    Prev
    Next
    INDEX
    Explanations

    the word "whether" and its variations in different contexts

    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
    oure
    -0.07
    abus
    -0.07
    vie
    -0.07
    oples
    -0.06
    #region
    -0.06
    loo
    -0.06
    atic
    -0.06
    allen
    -0.06
    един
    -0.06
    atinum
    -0.06
    POSITIVE LOGITS
     it
    0.08
     itu
    0.07
    ãģĿãĤĮãģ¯
    0.07
    Regards
    0.07
    StackNavigator
    0.07
     Äijó
    0.07
     Shi
    0.06
    soever
    0.06
    å®ĥ
    0.06
     ê·¸ê²ĥ
    0.06
    Activations Density 0.007%

    No Known Activations