© 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. 128111
    Prev
    Next
    INDEX
    Explanations

    punctuation and structure in the 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
     LENG
    -0.08
    ίÏĦ
    -0.07
    .appspot
    -0.07
    ë¨
    -0.07
    oka
    -0.07
    onna
    -0.07
    /qt
    -0.07
    onso
    -0.07
    ttp
    -0.07
    ,↵↵↵↵
    -0.07
    POSITIVE LOGITS
    vester
    0.06
    gross
    0.06
    éĦī
    0.06
     Gross
    0.06
    acity
    0.05
     Ud
    0.05
     Cons
    0.05
     cre
    0.05
    rength
    0.05
    gart
    0.05
    Activations Density 0.012%

    No Known Activations