© 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. 59724
    Prev
    Next
    INDEX
    Explanations

    references to ranking or classifications in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Common function words (especially prepositions followed by determiners) that introduce specific locations, objects or contextual information in descriptive text.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    .scalablytyped
    -0.08
    iolet
    -0.07
     @@↵
    -0.07
    Ù쨵ÙĦ
    -0.07
    ãĥ¼ãĥĦ
    -0.07
     Demon
    -0.07
    ,,,,,,,,
    -0.07
    ãĤĤãģĨ
    -0.06
     backpage
    -0.06
    ãģĸ
    -0.06
    POSITIVE LOGITS
     latter
    0.09
     both
    0.09
    both
    0.08
     each
    0.08
    Both
    0.07
     these
    0.07
    each
    0.07
    legg
    0.07
    tok
    0.07
     Both
    0.07
    Activations Density 0.074%

    No Known Activations