© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 89751
    Prev
    Next
    INDEX
    Explanations

    technical elements related to coding or markup languages

    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
    hos
    -0.07
    ardi
    -0.06
    roup
    -0.06
    uat
    -0.06
     counterpart
    -0.06
    ele
    -0.06
    oft
    -0.06
    rese
    -0.06
    umber
    -0.06
    osti
    -0.06
    POSITIVE LOGITS
     Karlov
    0.07
     Saunders
    0.06
    ιβ
    0.06
    輯
    0.06
    NPC
    0.06
    覺
    0.06
    frag
    0.06
     åıĮ线
    0.06
     çĻº
    0.06
     gates
    0.06
    Activations Density 0.001%

    No Known Activations