© 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. 17-LLAMASCOPE-RES-131K
    11. 125456
    Prev
    Next
    INDEX
    Explanations

    references to lotteries and related terms

    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
     vụ
    -0.07
    forth
    -0.07
    chaft
    -0.07
    /problems
    -0.07
     ëĶ°ë¥¸
    -0.07
     Mang
    -0.07
    akra
    -0.07
    elman
    -0.07
    chner
    -0.06
    zelf
    -0.06
    POSITIVE LOGITS
    tainment
    0.07
     cashier
    0.07
    MX
    0.06
    consin
    0.06
    ItemId
    0.06
    operators
    0.06
    landa
    0.06
     operators
    0.06
    ariant
    0.06
    bee
    0.06
    Activations Density 0.005%

    No Known Activations