© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 61790
    Prev
    Next
    INDEX
    Explanations

    programming-related discussions about handling conditions and events

    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
    TestFixture
    -0.07
     needles
    -0.07
    nist
    -0.07
    abay
    -0.06
    alone
    -0.06
     Bros
    -0.06
    unami
    -0.06
    brook
    -0.06
    tn
    -0.06
    rack
    -0.06
    POSITIVE LOGITS
    ยà¸ĩ
    0.07
    tek
    0.07
    å¢ĥ
    0.07
     Hüs
    0.07
    otionEvent
    0.07
     Gross
    0.06
    wand
    0.06
    essen
    0.06
    uru
    0.06
    COND
    0.06
    Activations Density 0.027%

    No Known Activations