© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 1244
    Prev
    Next
    INDEX
    Explanations

    definite articles preceding various nouns indicating structure or organization

    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
    ãĥ³ãĥĪ
    -0.08
    lesen
    -0.07
    å¹
    -0.07
    ILLISE
    -0.07
     presence
    -0.07
    iye
    -0.07
    -layout
    -0.07
     qua
    -0.07
    entai
    -0.07
    sie
    -0.07
    POSITIVE LOGITS
     series
    0.08
    PLICIT
    0.07
    ongo
    0.06
     ç³»
    0.06
    oval
    0.06
     chain
    0.06
    Ĥæķ°
    0.06
    (series
    0.06
     ongoing
    0.06
     bigger
    0.06
    Activations Density 0.012%

    No Known Activations