© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 125
    Prev
    Next
    INDEX
    Explanations

    event-related details such as timings and locations

    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
    istrovstvÃŃ
    -0.07
    ymoon
    -0.06
     Passenger
    -0.06
     opt
    -0.06
    ãĥ¬ãĤ¤
    -0.06
    orry
    -0.06
    alam
    -0.06
    Attend
    -0.06
    788
    -0.05
     Tribal
    -0.05
    POSITIVE LOGITS
     route
    0.08
    -route
    0.08
    route
    0.07
     Shapiro
    0.07
     Route
    0.07
    mov
    0.07
    .scalablytyped
    0.07
     Routes
    0.07
     routes
    0.07
    Route
    0.07
    Activations Density 0.022%

    No Known Activations