© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 89790
    Prev
    Next
    INDEX
    Explanations

    terms related to spatial relationships and dimensionality in art

    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
    es
    -0.07
     grant
    -0.06
     stay
    -0.06
     worldwide
    -0.06
    reme
    -0.06
     Mesh
    -0.06
     
    -0.06
    asset
    -0.06
     giant
    -0.05
    i
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.09
    ãĤ¤ãĥī
    0.09
    mite
    0.08
    ê½
    0.08
    ศาสà¸ķร
    0.08
    çĵľ
    0.08
    بÙĪØ§Ø³Ø·Ø©
    0.08
    Falsy
    0.08
    ìł¤
    0.08
    екÑĤи
    0.08
    Activations Density 0.013%

    No Known Activations