© 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. 5-LLAMASCOPE-RES-131K
    6. 125850
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to synonyms and their usage

    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
    lope
    -0.07
    Blank
    -0.07
    gear
    -0.06
    locker
    -0.06
    getObject
    -0.06
    loom
    -0.06
    ogan
    -0.06
    élé
    -0.06
    locking
    -0.06
    AdapterFactory
    -0.06
    POSITIVE LOGITS
    inecraft
    0.07
    ssp
    0.07
    ously
    0.07
    iny
    0.07
    Sdk
    0.06
    borg
    0.06
    IID
    0.06
    -Clause
    0.06
    PRETTY
    0.06
    .dtd
    0.06
    Activations Density 0.004%

    No Known Activations