© 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. 57774
    Prev
    Next
    INDEX
    Explanations

    phrases related to options and choices in product selections

    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
     вд
    -0.08
     Collections
    -0.07
    .Debugger
    -0.07
    Collections
    -0.07
    CriticalSection
    -0.06
    .PLL
    -0.06
    burg
    -0.06
    ozÃŃ
    -0.06
    uni
    -0.06
     Roose
    -0.06
    POSITIVE LOGITS
     equ
    0.06
    owie
    0.06
     inline
    0.06
     Miles
    0.06
     اÙĪÙĨ
    0.06
    bsolute
    0.06
     ül
    0.06
     Nam
    0.06
    ols
    0.06
    yw
    0.06
    Activations Density 0.002%

    No Known Activations