© 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. 17-LLAMASCOPE-RES-131K
    11. 93460
    Prev
    Next
    INDEX
    Explanations

    words associated with loud vocal expressions or reactions

    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
    ÑģÑĮ
    -0.06
    oit
    -0.06
    ÑĶм
    -0.06
    azaar
    -0.06
    oor
    -0.06
    uum
    -0.06
    ials
    -0.06
    oy
    -0.06
     Everest
    -0.06
     Woj
    -0.06
    POSITIVE LOGITS
    stakes
    0.10
    å¹ķ
    0.08
    antic
    0.08
    posium
    0.08
    writers
    0.08
    izoph
    0.08
     hã
    0.07
    loff
    0.07
    ergency
    0.07
    edback
    0.07
    Activations Density 0.004%

    No Known Activations