© 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. 4075
    Prev
    Next
    INDEX
    Explanations

    terms related to order cancellation processes

    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
    uraa
    -0.08
    «ĺ
    -0.07
    é
    -0.07
    اگ
    -0.07
    åĽ£
    -0.07
    cctor
    -0.07
    chyb
    -0.07
    alat
    -0.07
     credential
    -0.07
    ustil
    -0.07
    POSITIVE LOGITS
    gravity
    0.06
     manually
    0.06
     gravity
    0.06
     Commerce
    0.06
    ungi
    0.06
     discharged
    0.06
    okin
    0.06
     partial
    0.06
     pec
    0.06
     Partial
    0.06
    Activations Density 0.002%

    No Known Activations