© 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. 9-LLAMASCOPE-RES-131K
    11. 97483
    Prev
    Next
    INDEX
    Explanations

    references to legal expertise and professional credentials

    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
     Fo
    -0.06
    ért
    -0.06
     Cong
    -0.06
    dot
    -0.06
     FO
    -0.06
    Dirty
    -0.06
    NSS
    -0.06
     definition
    -0.06
     dot
    -0.05
    elib
    -0.05
    POSITIVE LOGITS
    ¶Į
    0.08
    à¹īาà¸Ļ
    0.08
     piger
    0.07
    SGlobal
    0.07
    alarından
    0.07
    å·±
    0.07
    коп
    0.07
    год
    0.07
     guarante
    0.07
    Pets
    0.07
    Activations Density 0.013%

    No Known Activations