© 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. 15-LLAMASCOPE-RES-131K
    11. 87529
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure elements related to Java development

    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
    uchos
    -0.07
    wargs
    -0.06
     Urs
    -0.06
    ---</
    -0.06
    \Context
    -0.06
    .bd
    -0.06
     novelty
    -0.06
    lediÄŁi
    -0.06
    기ê°Ģ
    -0.06
    åľ
    -0.06
    POSITIVE LOGITS
    orgia
    0.07
    emsp
    0.07
    lez
    0.07
    wich
    0.06
    roma
    0.06
     odv
    0.06
    ocache
    0.06
    omor
    0.06
    ycop
    0.06
    antal
    0.06
    Activations Density 0.006%

    No Known Activations