© 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. 57271
    Prev
    Next
    INDEX
    Explanations

    references to financial transactions or economic impacts

    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
    лÑĥг
    -0.07
    ama
    -0.06
    achel
    -0.06
     mark
    -0.06
    937
    -0.06
    ú
    -0.06
    808
    -0.06
    uno
    -0.06
    imer
    -0.06
    noon
    -0.06
    POSITIVE LOGITS
     continuing
    0.14
     continues
    0.14
     continue
    0.13
    continued
    0.13
     continued
    0.13
    continue
    0.13
     continu
    0.13
     continuation
    0.12
     continuar
    0.12
     resumed
    0.12
    Activations Density 0.165%

    No Known Activations