© 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. 127424
    Prev
    Next
    INDEX
    Explanations

    negations and their context in various scenarios

    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
    anna
    -0.07
    amp
    -0.06
     nonzero
    -0.06
    Ïĥα
    -0.06
    ales
    -0.06
     PURE
    -0.06
    æĢģ
    -0.06
    NON
    -0.06
    rieg
    -0.06
    ucus
    -0.06
    POSITIVE LOGITS
     بÙĦÚ©Ùĩ
    0.10
     necessarily
    0.10
     sino
    0.09
     but
    0.09
     sondern
    0.09
     anymore
    0.08
     usual
    0.08
    785
    0.07
    788
    0.07
     any
    0.07
    Activations Density 0.021%

    No Known Activations