© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77403
    Prev
    Next
    INDEX
    Explanations

    numeric identifiers for various items or categories

    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
    atat
    -0.07
    år
    -0.06
    orny
    -0.06
    íİ
    -0.06
    isz
    -0.06
    ÙħÙĤ
    -0.06
    esson
    -0.06
    reib
    -0.06
    aze
    -0.06
     CGRectGet
    -0.06
    POSITIVE LOGITS
    ]={↵
    0.06
     XCT
    0.06
    istrovstvÃŃ
    0.06
    åľ¨çº¿éĺħ读
    0.06
    ëĭĪëĭ¤
    0.06
     Booker
    0.06
    ÅĻÃŃ
    0.06
     Judge
    0.06
    enti
    0.06
     âŁ
    0.06
    Activations Density 0.000%

    No Known Activations