© 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. 15639
    Prev
    Next
    INDEX
    Explanations

    references to the experience level of professionals

    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
     Dixon
    -0.07
    TRY
    -0.07
    ubs
    -0.06
    åĿ
    -0.06
    rek
    -0.06
     Nicholson
    -0.06
     Lesser
    -0.06
    éļĨ
    -0.06
    esta
    -0.06
    itor
    -0.06
    POSITIVE LOGITS
     setHidden
    0.06
    .UnitTesting
    0.06
    adata
    0.06
    ADR
    0.06
     âĨĶ
    0.06
    üc
    0.06
    ux
    0.06
    avic
    0.06
    éļ
    0.06
     misunder
    0.06
    Activations Density 0.000%

    No Known Activations