© 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. 119099
    Prev
    Next
    INDEX
    Explanations

    references to totality or universality across various contexts

    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
    ovit
    -0.07
    letic
    -0.06
    atal
    -0.06
    nga
    -0.06
     inner
    -0.06
    iculo
    -0.06
     altogether
    -0.06
     miserable
    -0.06
    angkan
    -0.05
    ftar
    -0.05
    POSITIVE LOGITS
    .hw
    0.08
     ìĤ¬ëŀĮìĿĢ
    0.07
     humans
    0.07
    615
    0.07
    /classes
    0.07
    çļĨ
    0.07
     successful
    0.07
    ensation
    0.07
    ony
    0.07
    IService
    0.07
    Activations Density 0.027%

    No Known Activations