© 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. 40920
    Prev
    Next
    INDEX
    Explanations

    monetary values and their implications

    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
    æģµ
    -0.06
     Russo
    -0.06
    bid
    -0.06
    interop
    -0.06
    413
    -0.06
     shared
    -0.06
    uristic
    -0.06
    _ml
    -0.06
    anzeigen
    -0.06
    burgh
    -0.05
    POSITIVE LOGITS
     Cum
    0.07
     cumulative
    0.07
     cum
    0.07
    Affected
    0.07
    Cum
    0.07
    significant
    0.07
    Ïģκ
    0.06
     small
    0.06
    iffies
    0.06
    oca
    0.06
    Activations Density 0.024%

    No Known Activations