© 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. 17-LLAMASCOPE-RES-131K
    11. 56921
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structures

    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
    arkin
    -0.07
    amy
    -0.07
     mortal
    -0.07
    cq
    -0.06
     Schwar
    -0.06
     Wy
    -0.06
    YTE
    -0.06
    eck
    -0.06
    czy
    -0.06
    Ñģл
    -0.06
    POSITIVE LOGITS
     ()=>
    0.08
    ãĤ¯ãĥĪ
    0.07
    [:,:
    0.06
    ekil
    0.06
    shit
    0.06
    ",-
    0.06
    pun
    0.06
    ogle
    0.06
    /stdc
    0.06
     ()=>{↵
    0.06
    Activations Density 0.248%

    No Known Activations