© 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. 117805
    Prev
    Next
    INDEX
    Explanations

    URLs and references to web 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
     Pron
    -0.06
    afe
    -0.06
     AA
    -0.05
     Oz
    -0.05
     course
    -0.05
     K
    -0.05
    ssi
    -0.05
     Tee
    -0.05
    ANTE
    -0.05
     things
    -0.05
    POSITIVE LOGITS
    ÑĪиб
    0.07
    udder
    0.07
    رج
    0.07
     unp
    0.07
    angen
    0.07
     ((__
    0.07
    'gc
    0.07
    /conf
    0.07
    æľĢé«ĺ
    0.07
    ://
    0.06
    Activations Density 0.006%

    No Known Activations