© 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. 17-LLAMASCOPE-RES-131K
    6. 127242
    Prev
    Next
    INDEX
    Explanations

    specific terms and references related to gaming and educational institutions

    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
    quan
    -0.06
    afs
    -0.06
    .cc
    -0.06
    èµ·ãģĵ
    -0.06
    opsis
    -0.06
    CRET
    -0.06
    inte
    -0.06
    ạnh
    -0.05
     Hairst
    -0.05
    zion
    -0.05
    POSITIVE LOGITS
    deaux
    0.08
     Powered
    0.08
    Powered
    0.08
    RuntimeObject
    0.07
    TMP
    0.07
     âĢª
    0.06
    Uvs
    0.06
    Reload
    0.06
    TM
    0.06
    SM
    0.06
    Activations Density 0.101%

    No Known Activations