© 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. 59707
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant historical failures or unprecedented events

    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
    erken
    -0.08
    Disposed
    -0.07
    á»ijt
    -0.07
    isper
    -0.07
    oru
    -0.07
    ynom
    -0.07
    estar
    -0.07
    ensch
    -0.06
    boom
    -0.06
    neys
    -0.06
    POSITIVE LOGITS
     anywhere
    0.10
     previous
    0.10
     elsewhere
    0.09
     previously
    0.09
     since
    0.08
    previous
    0.08
     even
    0.08
     except
    0.07
     Previous
    0.07
     anything
    0.07
    Activations Density 0.011%

    No Known Activations