© 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 EvalsExportsinterp-engineNEWAPI 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. 79238
    Prev
    Next
    INDEX
    Explanations

    references to contradictions or oppositions in narratives or 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
     Walters
    -0.08
    ẽ
    -0.07
    еÑĢе
    -0.07
    ulan
    -0.07
    lor
    -0.06
    oyer
    -0.06
     æħ
    -0.06
    ç»Īäºİ
    -0.06
    ota
    -0.06
    oz
    -0.06
    POSITIVE LOGITS
     opposite
    0.28
     contrary
    0.17
     contrario
    0.15
     naopak
    0.14
     ngược
    0.14
     reverse
    0.14
     instead
    0.14
    åıį
    0.13
     oppos
    0.13
    inverse
    0.13
    Activations Density 0.077%

    No Known Activations