© 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. 15-LLAMASCOPE-RES-131K
    11. 90889
    Prev
    Next
    INDEX
    Explanations

    specific dates and temporal 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
    uien
    -0.07
    adge
    -0.06
    ông
    -0.06
     ragaz
    -0.06
    shiv
    -0.06
    mez
    -0.06
     комплек
    -0.06
     Rud
    -0.06
    artin
    -0.06
     Dir
    -0.06
    POSITIVE LOGITS
    aken
    0.08
    201
    0.07
    ç·Ĵ
    0.07
    illard
    0.07
    ffa
    0.07
    fy
    0.06
    reating
    0.06
    ronics
    0.06
    UGHT
    0.06
    lagen
    0.06
    Activations Density 0.011%

    No Known Activations