© 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. 58714
    Prev
    Next
    INDEX
    Explanations

    instances of negation or contrast in statements

    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
    orr
    -0.07
    rys
    -0.06
    rina
    -0.06
    ä¹Ļ
    -0.06
    pix
    -0.06
     frank
    -0.06
    ait
    -0.06
    /render
    -0.06
    Ãł
    -0.06
    zug
    -0.06
    POSITIVE LOGITS
     before
    0.14
     antes
    0.11
    before
    0.10
     Before
    0.10
    Before
    0.10
    -before
    0.09
     bevor
    0.09
    _before
    0.09
    	before
    0.09
     trÆ°á»Ľc
    0.08
    Activations Density 0.007%

    No Known Activations