© 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. 14811
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "resign" and its variations

    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
    باÙĨ
    -0.07
    bris
    -0.07
    strike
    -0.07
    kop
    -0.06
    anki
    -0.06
     Netz
    -0.06
    vider
    -0.06
    ÙĦÙĩ
    -0.06
     Grave
    -0.06
     öden
    -0.06
    POSITIVE LOGITS
    emean
    0.08
    ì§ģ
    0.07
    erp
    0.07
    AMESPACE
    0.07
     resignation
    0.07
     khá»ıi
    0.07
    atures
    0.07
    à¸ķำà¹ģหà¸Ļ
    0.06
    omics
    0.06
    etti
    0.06
    Activations Density 0.005%

    No Known Activations