© 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. 124933
    Prev
    Next
    INDEX
    Explanations

    words related to cessation or halting actions

    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
    หา
    -0.07
    ections
    -0.07
    kas
    -0.07
    eel
    -0.07
    issing
    -0.07
    ein
    -0.07
    кÑĥлÑı
    -0.07
    appa
    -0.07
    etter
    -0.07
    mpr
    -0.06
    POSITIVE LOGITS
     being
    0.09
     altogether
    0.08
    per
    0.08
    gap
    0.08
     making
    0.07
    -gap
    0.07
    AllWindows
    0.07
     ex
    0.07
    lessly
    0.06
     entirely
    0.06
    Activations Density 0.013%

    No Known Activations