© 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. 59868
    Prev
    Next
    INDEX
    Explanations

    references to government legislation and stimulus packages

    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
    ">//
    -0.08
    623
    -0.07
    úsqueda
    -0.07
    aub
    -0.06
     Clarkson
    -0.06
     Hillary
    -0.06
     preempt
    -0.06
    ìĬ¤íĭ°
    -0.06
    yer
    -0.06
     reform
    -0.06
    POSITIVE LOGITS
    antz
    0.08
    anch
    0.07
    ãģ£ãģ±
    0.07
    flate
    0.07
    dk
    0.06
     stimulus
    0.06
    acie
    0.06
    adar
    0.06
     Warp
    0.06
    Transmission
    0.06
    Activations Density 0.016%

    No Known Activations