© 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. 127448
    Prev
    Next
    INDEX
    Explanations

    activities and involvement in the arts and non-profit sectors

    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
    ãĥ©ãĥĥãĤ¯
    -0.09
    ÑĪкÑĥ
    -0.08
     (*((
    -0.08
    ijken
    -0.08
    Ø´ÙĨ
    -0.08
    eba
    -0.08
    yna
    -0.08
    fcn
    -0.08
    egra
    -0.07
    scribed
    -0.07
    POSITIVE LOGITS
     many
    0.10
     numerous
    0.09
     countless
    0.08
     zahl
    0.07
     hundreds
    0.07
    many
    0.07
     several
    0.07
     over
    0.07
    clid
    0.07
    /is
    0.06
    Activations Density 0.028%

    No Known Activations