© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 60084
    Prev
    Next
    INDEX
    Explanations

    terms associated with academic roles and organizational structures

    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
    jian
    -0.06
     break
    -0.06
    xyz
    -0.06
    &gt
    -0.05
    unity
    -0.05
    ÏĢοÏĦε
    -0.05
     total
    -0.05
     Arena
    -0.05
    Greater
    -0.05
     Municipal
    -0.05
    POSITIVE LOGITS
    @nate
    0.08
    /umd
    0.08
    apon
    0.07
    lä
    0.06
    elda
    0.06
     UNU
    0.06
    ertas
    0.06
    é§ħå¾ĴæŃ©
    0.06
    ptal
    0.06
    agal
    0.06
    Activations Density 0.008%

    No Known Activations