© 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. 78250
    Prev
    Next
    INDEX
    Explanations

    mentions of economic regulations and their implications

    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
    rang
    -0.06
    анÑĮ
    -0.06
     rang
    -0.06
    Ø´Ùĩ
    -0.06
    zin
    -0.06
    ãģĹãĤĩ
    -0.06
    าà¸į
    -0.06
    ulk
    -0.06
     Vanity
    -0.06
    ery
    -0.06
    POSITIVE LOGITS
     exempt
    0.14
     immune
    0.13
     immunity
    0.10
     exemption
    0.10
     untouched
    0.10
     spared
    0.10
     exceptions
    0.10
     remained
    0.10
    immune
    0.10
    exceptions
    0.10
    Activations Density 0.074%

    No Known Activations