© 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. 107105
    Prev
    Next
    INDEX
    Explanations

    terms related to industrial processes and products

    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
    ullo
    -0.07
    etty
    -0.07
     Proud
    -0.07
    ulum
    -0.06
     æŃ
    -0.06
    etti
    -0.06
    umar
    -0.06
    acher
    -0.06
    emens
    -0.06
    ech
    -0.06
    POSITIVE LOGITS
     across
    0.07
     Kirby
    0.06
    à¤Ŀ
    0.06
     gen
    0.06
    _errno
    0.06
     cong
    0.06
    pes
    0.06
    ãĥ¼ãĥį
    0.06
    employed
    0.06
    odos
    0.06
    Activations Density 0.002%

    No Known Activations