© 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. 127644
    Prev
    Next
    INDEX
    Explanations

    technical specifications and data

    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
    üz
    -0.08
    roids
    -0.08
    .liferay
    -0.07
    .gradient
    -0.07
    portun
    -0.07
    pch
    -0.07
    anean
    -0.07
    rema
    -0.07
    berapa
    -0.07
    sdk
    -0.07
    POSITIVE LOGITS
     wings
    0.12
     Wings
    0.10
    wing
    0.09
    pan
    0.08
     wing
    0.08
     spread
    0.07
    apan
    0.06
     Wing
    0.06
     longest
    0.06
     Spread
    0.06
    Activations Density 0.014%

    No Known Activations