© 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. 31325
    Prev
    Next
    INDEX
    Explanations

    phrases indicating internal conflict or emotional struggles

    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
    onya
    -0.08
    ansk
    -0.07
    пион
    -0.07
    infos
    -0.07
    eldom
    -0.07
    zych
    -0.07
    جد
    -0.07
    bye
    -0.07
     Recorder
    -0.07
    illa
    -0.07
    POSITIVE LOGITS
    ãĥ«ãĥķ
    0.07
     maybe
    0.06
     Plum
    0.06
    507
    0.06
     fucking
    0.06
    LEC
    0.05
    ida
    0.05
    zo
    0.05
     like
    0.05
    inson
    0.05
    Activations Density 0.083%

    No Known Activations