© 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. 9-LLAMASCOPE-RES-131K
    11. 95742
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols in legal or formal text

    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
    iland
    -0.06
     NavParams
    -0.06
    assen
    -0.06
    ylon
    -0.06
    iesen
    -0.05
    iversity
    -0.05
    Insensitive
    -0.05
    olas
    -0.05
    iger
    -0.05
    nelle
    -0.05
    POSITIVE LOGITS
    Ñıж
    0.08
    \Context
    0.07
    .throw
    0.07
     aday
    0.07
    äºĭæ¥Ń
    0.07
    дам
    0.07
     McGregor
    0.07
    ÑĢек
    0.07
    ÑĢоÑĦ
    0.07
    جÙĨ
    0.07
    Activations Density 0.001%

    No Known Activations