© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87882
    Prev
    Next
    INDEX
    Explanations

    file formats related to images and documents, particularly JPEG and PDF

    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
    ıa
    -0.06
    uilt
    -0.06
    svn
    -0.06
     "
    -0.06
    ear
    -0.05
    to
    -0.05
     xml
    -0.05
    ÑģÑĤва
    -0.05
    ady
    -0.05
    emand
    -0.05
    POSITIVE LOGITS
    ãĥĨãĥ«
    0.09
    ãĥ³ãĥĸ
    0.08
    iaux
    0.07
    à¥Ģà¤ıम
    0.07
    /jpeg
    0.07
    æķ¦
    0.07
    ÑĢож
    0.07
    ãģĭãģij
    0.06
    ìĿ´ìĸ´
    0.06
    çĭ¼
    0.06
    Activations Density 0.000%

    No Known Activations