© 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. 119600
    Prev
    Next
    INDEX
    Explanations

    terms related to the impact or effects of regulations on rights, health, and financial matters

    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
     sogar
    -0.07
    adin
    -0.07
    INUX
    -0.07
    ertain
    -0.07
    ilon
    -0.07
    isque
    -0.07
    ensburg
    -0.07
    isoft
    -0.06
     اÙĦÙħÙĨ
    -0.06
    nette
    -0.06
    POSITIVE LOGITS
     nor
    0.18
     or
    0.12
     anymore
    0.12
     Nor
    0.11
    nor
    0.11
     either
    0.10
     anything
    0.10
     any
    0.10
    Nor
    0.10
     neither
    0.10
    Activations Density 0.041%

    No Known Activations