© 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. 74726
    Prev
    Next
    INDEX
    Explanations

    references to the United States and associated entities or activities

    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
    imi
    -0.07
    amax
    -0.06
    leh
    -0.06
    armor
    -0.06
    /browse
    -0.06
     flavors
    -0.06
    ajar
    -0.06
    arsity
    -0.06
    278
    -0.06
    qv
    -0.06
    POSITIVE LOGITS
    edii
    0.07
    Sidebar
    0.07
    oons
    0.06
     باش
    0.06
    awaiter
    0.06
    ogh
    0.06
    IDES
    0.06
    /Dk
    0.06
    HRESULT
    0.06
    ieder
    0.06
    Activations Density 0.045%

    No Known Activations