© 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. 108402
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the passage of time and historical references

    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
    abei
    -0.07
    reste
    -0.07
    Çİ
    -0.07
     Rush
    -0.07
    à¸Ľà¸£à¸°à¸§
    -0.07
    ead
    -0.07
    ele
    -0.07
    aec
    -0.07
    ãĥªãĤ«
    -0.07
    еж
    -0.07
    POSITIVE LOGITS
     when
    0.07
     days
    0.07
    199
    0.06
    0.06
     childhood
    0.06
     before
    0.06
    196
    0.06
     mur
    0.06
    when
    0.06
    est
    0.06
    Activations Density 0.009%

    No Known Activations