© 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. 59319
    Prev
    Next
    INDEX
    Explanations

    file paths and references to data or resource locations in programming contexts

    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
    CCR
    -0.06
    ÅĻÃŃ
    -0.06
     Kath
    -0.05
    //**↵
    -0.05
     tez
    -0.05
     (+
    -0.05
     ins
    -0.05
    ETH
    -0.05
    翼
    -0.05
    ebi
    -0.05
    POSITIVE LOGITS
    ->{_
    0.08
    .OUT
    0.07
    otron
    0.07
    .Parcel
    0.07
    .mybatisplus
    0.07
    outfile
    0.07
    myModal
    0.07
    tmp
    0.07
    rotch
    0.07
    ClientRect
    0.07
    Activations Density 0.009%

    No Known Activations