© 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. 17-LLAMASCOPE-RES-131K
    6. 83895
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "default" in various contexts

    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
    atar
    -0.08
    iffin
    -0.07
    otify
    -0.07
    izzard
    -0.07
    anim
    -0.07
    aska
    -0.06
    modifiable
    -0.06
    ë§ī
    -0.06
    isan
    -0.06
    iral
    -0.06
    POSITIVE LOGITS
    ;display
    0.07
     gan
    0.06
    (cuda
    0.06
    CHANT
    0.06
    PPER
    0.06
     eg
    0.06
    ovan
    0.06
    UNC
    0.06
    ipeg
    0.06
    iez
    0.06
    Activations Density 0.004%

    No Known Activations