© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 27558
    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
    ãģ£ãģį
    -0.08
    icher
    -0.08
    вÑĸÑĤ
    -0.08
    Ģ
    -0.07
    azor
    -0.07
    ãĤĵãģ¨
    -0.07
    //--
    -0.07
    ubat
    -0.07
    ITTE
    -0.07
    vro
    -0.07
    POSITIVE LOGITS
     Sandy
    0.06
    â̦↵
    0.06
    ecast
    0.06
     tanto
    0.05
    x
    0.05
    cház
    0.05
    623
    0.05
    por
    0.05
    ets
    0.05
    ioni
    0.05
    Activations Density 0.014%

    No Known Activations