© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 126555
    Prev
    Next
    INDEX
    Explanations

    terms related to construction and structural components

    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
    eature
    -0.07
     teb
    -0.07
     ÑĩÑĤобÑĭ
    -0.07
    eatures
    -0.06
     Screw
    -0.06
    iaux
    -0.06
    'gc
    -0.06
    961
    -0.06
    chematic
    -0.06
    èm
    -0.06
    POSITIVE LOGITS
     due
    0.10
    due
    0.09
     sometimes
    0.08
     بسبب
    0.08
    _due
    0.08
     Due
    0.07
     occasionally
    0.07
    ometimes
    0.06
     frequently
    0.06
    Due
    0.06
    Activations Density 0.056%

    No Known Activations