© 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. 106297
    Prev
    Next
    INDEX
    Explanations

    instances or references of the word "disappear" and its variants

    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
    ollider
    -0.07
    yle
    -0.07
    ted
    -0.07
    .amazonaws
    -0.07
    uran
    -0.06
    /org
    -0.06
    ran
    -0.06
    spacer
    -0.06
    æĵ
    -0.06
    ÑĢив
    -0.06
    POSITIVE LOGITS
     khá»ıi
    0.09
     trace
    0.09
    æİī
    0.08
    ances
    0.08
    ostel
    0.07
    antly
    0.07
     altogether
    0.07
    /dis
    0.07
     traces
    0.07
    ously
    0.07
    Activations Density 0.009%

    No Known Activations