© 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. 124814
    Prev
    Next
    INDEX
    Explanations

    references to the relevance and consistency of concepts over time

    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
    ordum
    -0.07
    âng
    -0.07
    orden
    -0.07
    oux
    -0.06
    uw
    -0.06
    riott
    -0.06
    unj
    -0.06
    evin
    -0.06
    ijken
    -0.06
    ìŀ¬
    -0.06
    POSITIVE LOGITS
     original
    0.11
     ORIGINAL
    0.10
    original
    0.10
    _original
    0.09
     originally
    0.09
    -original
    0.09
     originals
    0.09
     Original
    0.09
     оÑĢиг
    0.09
    Original
    0.09
    Activations Density 0.012%

    No Known Activations