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. 77214
    Prev
    Next
    INDEX
    Explanations

    references to Java and JUnit libraries in code

    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
    PELL
    -0.07
     Chung
    -0.06
    ilip
    -0.06
    ordes
    -0.06
    icari
    -0.06
    onz
    -0.06
    uxt
    -0.06
    ừng
    -0.06
    atty
    -0.06
    ê²½
    -0.06
    POSITIVE LOGITS
    RuleContext
    0.07
    UCCEEDED
    0.07
    ãģªãĤī
    0.06
    ãĥ£
    0.06
    APON
    0.06
     +%
    0.06
    resh
    0.06
    iÄħ
    0.06
    uvw
    0.06
     Boeh
    0.06
    Activations Density 0.001%

    No Known Activations