© 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. 76593
    Prev
    Next
    INDEX
    Explanations

    references to speculation and leaks in media content

    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
    asl
    -0.06
     Statement
    -0.06
    lag
    -0.06
     programme
    -0.05
     Wahl
    -0.05
    yi
    -0.05
    ·
    -0.05
     helm
    -0.05
    etch
    -0.05
     grid
    -0.05
    POSITIVE LOGITS
    /ns
    0.07
    uzzi
    0.07
    缼
    0.07
    .gt
    0.07
     cancelButtonTitle
    0.07
    à¥ĭà¤ĸ
    0.07
     leak
    0.07
    SGlobal
    0.07
     Colleg
    0.06
    ëĮĢë¡ľ
    0.06
    Activations Density 0.008%

    No Known Activations