© 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. 17-LLAMASCOPE-RES-131K
    11. 56527
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific individual or topic

    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
    nia
    -0.08
    ober
    -0.08
    ultur
    -0.07
    rypton
    -0.07
     Ù¾ÛĮÚ©
    -0.07
    apolis
    -0.07
    regor
    -0.07
    ValueCollection
    -0.07
    _AUX
    -0.07
    507
    -0.07
    POSITIVE LOGITS
     Unity
    0.07
     UNITY
    0.06
    алеж
    0.06
     Dion
    0.06
    elin
    0.06
    æ¬ł
    0.06
    ingle
    0.06
    .addTo
    0.06
     Unified
    0.05
    ijd
    0.05
    Activations Density 0.000%

    No Known Activations