© 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. 41196
    Prev
    Next
    INDEX
    Explanations

    patterns of commitment and routine in artistic practices

    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
    ezi
    -0.07
     exhaustion
    -0.06
     Exhaust
    -0.06
    -0.06
     Kang
    -0.06
    emory
    -0.06
    uft
    -0.06
    apl
    -0.05
    ool
    -0.05
     Cone
    -0.05
    POSITIVE LOGITS
    senal
    0.07
    /WebAPI
    0.07
     ÙģرÙĪدگاÙĩ
    0.07
    ILLISE
    0.07
    GetPosition
    0.07
    ailles
    0.07
    Regressor
    0.07
    -webpack
    0.07
    ÃŃsto
    0.07
    UBE
    0.07
    Activations Density 0.024%

    No Known Activations