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

    Neuronpedia

    Jacobian LensNEW
    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. 57382
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate educational qualifications and certifications

    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
    pars
    -0.07
    peria
    -0.06
    abe
    -0.06
    abis
    -0.06
    hardt
    -0.06
    hoo
    -0.06
    aptor
    -0.06
    anner
    -0.06
    ourg
    -0.06
    premium
    -0.06
    POSITIVE LOGITS
     focus
    0.09
     focuses
    0.07
     minors
    0.07
     Minor
    0.07
    focus
    0.07
     focused
    0.06
    ijing
    0.06
     minor
    0.06
    лика
    0.06
     koc
    0.06
    Activations Density 0.009%

    No Known Activations