© 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 EvalsExportsinterp-engineNEWAPI 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. 27730
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to regulations and compliance

    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
    æĮģãģ¡
    -0.07
    :
    -0.06
    711
    -0.06
    Æ°u
    -0.05
     Hoch
    -0.05
    Īëĭ¤
    -0.05
    uku
    -0.05
     counter
    -0.05
     count
    -0.05
    si
    -0.05
    POSITIVE LOGITS
     if
    0.14
     nếu
    0.13
     jika
    0.12
     when
    0.12
     еÑģли
    0.11
     إذا
    0.11
     unless
    0.10
     wenn
    0.10
    å¦Ĥæŀľ
    0.10
     à¤ħà¤Ĺर
    0.10
    Activations Density 0.181%

    No Known Activations