© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 71633
    Prev
    Next
    INDEX
    Explanations

    references to personal artifacts or heirlooms with sentimental value

    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
     Slee
    -0.07
    çķª
    -0.07
    burgh
    -0.06
     inf
    -0.06
     Grat
    -0.06
    ataire
    -0.06
     Garn
    -0.06
     fatal
    -0.06
     Bracket
    -0.06
    stoff
    -0.06
    POSITIVE LOGITS
     UNUSED
    0.07
     keys
    0.07
     Keys
    0.07
     dụng
    0.07
    -unused
    0.07
     microscope
    0.07
    iete
    0.07
    éĹĺ
    0.07
    Ùģر
    0.07
    bij
    0.07
    Activations Density 0.072%

    No Known Activations