© 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. 60840
    Prev
    Next
    INDEX
    Explanations

    references to economic instability and financial crises

    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
    /Dk
    -0.08
     prostitutas
    -0.08
    pora
    -0.07
    ppv
    -0.07
    Uvs
    -0.07
    LTR
    -0.07
     Siber
    -0.07
    ëŀľëĵľ
    -0.07
    .scalablytyped
    -0.07
    год
    -0.07
    POSITIVE LOGITS
     Drag
    0.07
     Greek
    0.07
     Euro
    0.07
     Greece
    0.07
    drag
    0.06
     euro
    0.06
    rig
    0.06
     contag
    0.06
     rig
    0.06
     Maiden
    0.06
    Activations Density 0.019%

    No Known Activations