© 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. 120895
    Prev
    Next
    INDEX
    Explanations

    identifiers or codes related to specifications or configurations in a technical or administrative context

    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
    argo
    -0.07
    .enumer
    -0.07
    190
    -0.06
    idden
    -0.06
    etically
    -0.06
    ãģĿãģ®ä»ĸ
    -0.06
    ollah
    -0.06
    tein
    -0.06
    rike
    -0.06
    CT
    -0.06
    POSITIVE LOGITS
    deniz
    0.07
    /pages
    0.07
     Annunci
    0.06
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    0.06
     Sokol
    0.06
    αι
    0.06
     merk
    0.06
    Volumes
    0.06
    عÙĦ
    0.06
    ACHINE
    0.06
    Activations Density 0.016%

    No Known Activations