© 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. 62284
    Prev
    Next
    INDEX
    Explanations

    concepts related to understanding and inference

    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
    ault
    -0.06
    lash
    -0.06
    atham
    -0.06
    spiel
    -0.06
    215
    -0.06
    holder
    -0.06
    holds
    -0.06
    hle
    -0.06
     Cathedral
    -0.06
    745
    -0.06
    POSITIVE LOGITS
    Fabric
    0.06
    εβ
    0.06
    engeance
    0.06
     дли
    0.06
    ابر
    0.06
     Scalars
    0.06
    ScreenState
    0.06
    fabric
    0.06
    lington
    0.06
    eka
    0.06
    Activations Density 0.002%

    No Known Activations