© 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. 126552
    Prev
    Next
    INDEX
    Explanations

    negations and negative phrases

    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
    ogan
    -0.07
    speaker
    -0.07
    bane
    -0.07
    sts
    -0.06
    onse
    -0.06
    ousel
    -0.06
     æ°
    -0.06
    Æ¡
    -0.06
    лем
    -0.06
    otive
    -0.06
    POSITIVE LOGITS
     alone
    0.17
     Alone
    0.13
    alone
    0.13
     sole
    0.12
     saja
    0.11
    -alone
    0.10
    åĶ¯ä¸Ģ
    0.09
    ë¿IJ
    0.09
     only
    0.09
     seul
    0.09
    Activations Density 0.012%

    No Known Activations