© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77651
    Prev
    Next
    INDEX
    Explanations

    technical terms related to telecommunications and devices used for communication

    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
    725
    -0.06
     simp
    -0.06
    892
    -0.06
    847
    -0.06
    inois
    -0.06
    853
    -0.06
    852
    -0.06
    829
    -0.06
    891
    -0.06
     up
    -0.06
    POSITIVE LOGITS
    âijł
    0.08
    âĢ»
    0.07
    ignet
    0.07
     Ðļа
    0.07
     Zem
    0.07
    imd
    0.07
    大人
    0.07
    RYPT
    0.06
    oplay
    0.06
    eya
    0.06
    Activations Density 0.007%

    No Known Activations