© 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. 29559
    Prev
    Next
    INDEX
    Explanations

    terms related to tasks or objectives

    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
    urdu
    -0.07
     Ih
    -0.06
    àµ
    -0.06
    anness
    -0.06
    ViewChild
    -0.06
    OrNil
    -0.06
    ynos
    -0.06
     å¾
    -0.06
    (ARG
    -0.06
     Queen
    -0.06
    POSITIVE LOGITS
    аÑİ
    0.07
    UPI
    0.06
     Pipes
    0.06
     ìĿ´ë²Ī
    0.06
     Petit
    0.06
    .png
    0.06
    quisite
    0.06
    shall
    0.06
     آزÙħ
    0.06
    _UNDEFINED
    0.06
    Activations Density 0.001%

    No Known Activations