© 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. 15-LLAMASCOPE-RES-131K
    6. 1451
    Prev
    Next
    INDEX
    Explanations

    instances of the word "was" used in various contexts

    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
    tti
    -0.07
    ivent
    -0.06
    velt
    -0.06
     orders
    -0.06
     Eld
    -0.06
     Steph
    -0.06
    iid
    -0.06
    ستاÙĨ
    -0.06
    ertino
    -0.06
    ãĥ¼ãĥ³
    -0.06
    POSITIVE LOGITS
    ãĥ©ãĤ¯
    0.08
    nings
    0.07
    -addons
    0.07
    Schedulers
    0.06
    dan
    0.06
    åıĤ
    0.06
    HLT
    0.06
     legion
    0.06
    ë¹ĦìķĦ
    0.06
    /loader
    0.06
    Activations Density 0.006%

    No Known Activations