© 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. 9-LLAMASCOPE-RES-131K
    11. 95538
    Prev
    Next
    INDEX
    Explanations

    interactivity and trivia-related content

    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
    ifu
    -0.08
    ptrdiff
    -0.07
    èn
    -0.07
    ductive
    -0.07
    mund
    -0.06
    uitka
    -0.06
    icken
    -0.06
    ellar
    -0.06
    metis
    -0.06
    alars
    -0.06
    POSITIVE LOGITS
    iena
    0.06
    opa
    0.06
    /ng
    0.06
    èĻİ
    0.06
     Pla
    0.06
    uez
    0.05
    ertino
    0.05
    oser
    0.05
    AbsolutePath
    0.05
     relieved
    0.05
    Activations Density 0.006%

    No Known Activations