© 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. 15909
    Prev
    Next
    INDEX
    Explanations

    programmatic terms related to assistance and benefits in community initiatives

    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
    estre
    -0.07
    .ie
    -0.07
    ansk
    -0.07
    ekl
    -0.07
    odge
    -0.07
     spokesman
    -0.07
    bos
    -0.06
    acam
    -0.06
    .swt
    -0.06
    ród
    -0.06
    POSITIVE LOGITS
    viso
    0.06
     gran
    0.06
     Gran
    0.06
    uer
    0.06
     seed
    0.06
     statewide
    0.06
    wap
    0.06
     cư
    0.06
     identified
    0.06
     exclusive
    0.06
    Activations Density 0.001%

    No Known Activations