© 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. 16006
    Prev
    Next
    INDEX
    Explanations

    terms related to professional development and job market trends

    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
    lege
    -0.07
    .Actions
    -0.06
    Providers
    -0.06
     cheap
    -0.06
     Cheap
    -0.06
    -signed
    -0.06
    arend
    -0.06
    atile
    -0.06
    [](
    -0.06
    رÛĮاÙĨ
    -0.06
    POSITIVE LOGITS
     candidate
    0.08
    unicorn
    0.07
     positions
    0.07
    åĬ
    0.07
     lateral
    0.07
     вак
    0.07
    ulis
    0.07
     candidates
    0.07
    candidate
    0.07
    ween
    0.07
    Activations Density 0.005%

    No Known Activations