© 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. 16755
    Prev
    Next
    INDEX
    Explanations

    references to product models and updates

    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
     disclaimer
    -0.05
    ince
    -0.05
     becoming
    -0.05
    erno
    -0.05
    iled
    -0.05
     Wil
    -0.05
     sub
    -0.05
    ãĤ¤ãĤº
    -0.05
    oto
    -0.05
     remains
    -0.05
    POSITIVE LOGITS
    ãģ«ãģ¯
    0.09
    ìĹIJëĬĶ
    0.09
     contain
    0.09
    contain
    0.09
     contains
    0.09
    ìĹIJëıĦ
    0.08
    contains
    0.08
    обов
    0.08
    ãģ«ãĤĤ
    0.08
    PEC
    0.07
    Activations Density 0.047%

    No Known Activations