© 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. 3579
    Prev
    Next
    INDEX
    Explanations

    references to animated GIFs and audio files

    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
    	freopen
    -0.07
    erer
    -0.06
    tere
    -0.06
    lain
    -0.06
    iphers
    -0.06
     Foley
    -0.06
     Serif
    -0.05
     Pdf
    -0.05
    overe
    -0.05
    ConfigurationException
    -0.05
    POSITIVE LOGITS
    teenth
    0.10
    /gif
    0.09
    ;base
    0.08
    aget
    0.07
     anim
    0.07
    IELDS
    0.07
    ipeg
    0.07
    dbg
    0.07
    anic
    0.07
    ibbon
    0.07
    Activations Density 0.001%

    No Known Activations