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

    Neuronpedia

    Jacobian LensNEW
    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. 59526
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate ongoing actions or states

    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
    iler
    -0.07
    енз
    -0.07
    itzer
    -0.07
    мовÑĸÑĢ
    -0.07
    elib
    -0.07
    ILER
    -0.07
    Ã¶ÃŁe
    -0.07
    egan
    -0.06
    bis
    -0.06
    usercontent
    -0.06
    POSITIVE LOGITS
     lately
    0.07
    errat
    0.06
     ade
    0.06
    Cod
    0.06
     forever
    0.06
     Alam
    0.06
    dez
    0.06
    Įĵ
    0.05
    recent
    0.05
     overtime
    0.05
    Activations Density 0.027%

    No Known Activations