© 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. 5-LLAMASCOPE-RES-131K
    11. 126605
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "long."

    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
    ansom
    -0.08
    idal
    -0.08
    .Perform
    -0.07
    dın
    -0.07
    intree
    -0.07
     Radi
    -0.07
    chner
    -0.07
    ãĤĪãĤĬ
    -0.07
    à¹ĥà¸Ī
    -0.06
    ILLISECONDS
    -0.06
    POSITIVE LOGITS
    s
    0.08
     necessary
    0.07
     Cust
    0.06
    ico
    0.06
    necessary
    0.06
    wick
    0.06
    ÙĨاÙĨ
    0.06
    ICO
    0.06
    addock
    0.06
     until
    0.05
    Activations Density 0.004%

    No Known Activations