© 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. 106327
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the importance or significance of information being presented

    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
    eson
    -0.07
    ogan
    -0.06
    ž
    -0.06
    zan
    -0.06
    ynes
    -0.06
    .si
    -0.06
    thon
    -0.06
     disconnect
    -0.06
    ches
    -0.05
     Schn
    -0.05
    POSITIVE LOGITS
    erdale
    0.08
    çļĦæĺ¯
    0.07
    è¾°
    0.07
    ẩm
    0.07
    egasus
    0.07
    ä¸Ģä¸ĭ
    0.07
    registr
    0.07
    enance
    0.07
    ableView
    0.06
    RunWith
    0.06
    Activations Density 0.009%

    No Known Activations