© 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. 30061
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of exploration

    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
    emain
    -0.08
    iker
    -0.08
    haar
    -0.07
    kola
    -0.07
    enge
    -0.07
    ido
    -0.07
    ook
    -0.07
    unn
    -0.07
    د
    -0.07
    uracy
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĥŃ
    0.07
    ãĥĥãĤ°
    0.07
    AYOUT
    0.06
    orrect
    0.06
    ary
    0.06
    åĦ
    0.06
    rence
    0.06
    sole
    0.06
    ŀæĢ§
    0.06
    ìĥī
    0.06
    Activations Density 0.018%

    No Known Activations