© 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. 17123
    Prev
    Next
    INDEX
    Explanations

    phrases related to government initiatives and regulatory actions

    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
    kir
    -0.06
     Mits
    -0.06
    styl
    -0.06
    wu
    -0.06
    echa
    -0.06
    _cpp
    -0.06
    ек
    -0.06
     autobiography
    -0.06
     Maul
    -0.06
    blr
    -0.06
    POSITIVE LOGITS
     deliberate
    0.07
     exclusively
    0.07
     coordination
    0.06
     Coord
    0.06
     sole
    0.06
    eron
    0.06
     cal
    0.06
    ãĥ¼ãĤ¿ãĥ¼
    0.06
    aler
    0.06
     prom
    0.06
    Activations Density 0.036%

    No Known Activations