© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82168
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names

    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
    ondo
    -0.07
    å¦
    -0.07
    .zip
    -0.07
    ãĤ¾
    -0.07
    ãģĶ
    -0.07
    apan
    -0.07
    год
    -0.06
    uddle
    -0.06
    ông
    -0.06
    .rar
    -0.06
    POSITIVE LOGITS
     Uncategorized
    0.12
    achte
    0.08
     tagged
    0.07
    LLLL
    0.06
     ex
    0.06
     CancellationToken
    0.06
    .wp
    0.06
     org
    0.06
    Posted
    0.06
    Slider
    0.06
    Activations Density 0.017%

    No Known Activations