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

    Neuronpedia

    Jacobian LensNEW
    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. 59071
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating the end of sentences or thoughts

    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
    vs
    -0.06
     Que
    -0.06
    宫
    -0.06
    zcze
    -0.06
     Nad
    -0.06
    fs
    -0.06
    illas
    -0.06
     fats
    -0.06
     portion
    -0.05
     Tong
    -0.05
    POSITIVE LOGITS
    å¡
    0.07
    ahy
    0.07
    ÑİÑĢ
    0.07
    ãĥ¥ãĥ¼
    0.07
    CJK
    0.07
     ανά
    0.06
    oble
    0.06
    VertexArray
    0.06
     اÙĦرسÙħÙĬ
    0.06
    ÑĢÑĥк
    0.06
    Activations Density 0.003%

    No Known Activations