Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 76637
    Prev
    Next
    INDEX
    Explanations

    concepts related to natural products and their distinction from money

    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
    mach
    -0.07
    erd
    -0.06
    zy
    -0.06
    bbc
    -0.06
    eps
    -0.06
    rgan
    -0.06
    lid
    -0.06
    olute
    -0.06
    igid
    -0.06
    سÙĨ
    -0.06
    POSITIVE LOGITS
    ãĤ¿ãĥ³
    0.07
    ossa
    0.07
     copies
    0.06
    -produced
    0.06
     tang
    0.06
     Costs
    0.06
    @testable
    0.06
     enjoyment
    0.06
    share
    0.06
    -produ
    0.06
    Activations Density 0.002%

    No Known Activations