© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 61361
    Prev
    Next
    INDEX
    Explanations

    economic trends and their impacts on various sectors

    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
    imus
    -0.07
    obia
    -0.06
     coursework
    -0.06
    istringstream
    -0.06
    amine
    -0.06
    oten
    -0.06
    elle
    -0.06
    oload
    -0.06
     extrem
    -0.06
    oš
    -0.05
    POSITIVE LOGITS
     unfavorable
    0.06
     Dur
    0.06
    ncia
    0.06
     fewer
    0.06
    ayet
    0.06
     onCancelled
    0.06
    iyor
    0.06
     nh
    0.06
    çµ±
    0.06
    llib
    0.06
    Activations Density 0.019%

    No Known Activations