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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 84143
    Prev
    Next
    INDEX
    Explanations

    product-related details, particularly for various types of items and equipment

    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
    ży
    -0.06
     Classics
    -0.06
     Romero
    -0.06
    Assembler
    -0.06
     Dumpster
    -0.06
     shorthand
    -0.06
    Ø´Ùħ
    -0.06
    룡
    -0.05
    /apt
    -0.05
    Lint
    -0.05
    POSITIVE LOGITS
    opup
    0.07
    .rpm
    0.07
    aldi
    0.07
    duct
    0.07
    elin
    0.06
    nete
    0.06
    缴
    0.06
    xoops
    0.06
     chất
    0.06
     è¡
    0.06
    Activations Density 0.011%

    No Known Activations