© 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. 71425
    Prev
    Next
    INDEX
    Explanations

    numerical data, particularly pertaining to research findings

    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
    pedia
    -0.06
    åŀ
    -0.06
    θη
    -0.06
     Wikip
    -0.06
     авÑĤомаÑĤи
    -0.06
    hart
    -0.06
     oslo
    -0.05
    .ua
    -0.05
     Wikipedia
    -0.05
    compat
    -0.05
    POSITIVE LOGITS
    maal
    0.07
    AINED
    0.07
    kker
    0.07
    iert
    0.07
     indem
    0.07
    ItemSelected
    0.07
     [](
    0.06
    vier
    0.06
    UZ
    0.06
    uppen
    0.06
    Activations Density 0.002%

    No Known Activations