© 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. 5-LLAMASCOPE-RES-131K
    11. 125558
    Prev
    Next
    INDEX
    Explanations

    structures or patterns in code and configuration settings

    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
    Ð¡Ð¡Ðł
    -0.07
     Nimbus
    -0.07
    assis
    -0.06
    yet
    -0.06
    pit
    -0.06
     ironically
    -0.06
    że
    -0.06
    498
    -0.06
    iou
    -0.06
    owner
    -0.06
    POSITIVE LOGITS
     annunci
    0.07
    swick
    0.06
    lagen
    0.06
    ildenafil
    0.06
    ekil
    0.06
     XCTAssertTrue
    0.06
    loys
    0.06
    Frameworks
    0.05
    .timedelta
    0.05
     comm
    0.05
    Activations Density 0.016%

    No Known Activations