© 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. 77619
    Prev
    Next
    INDEX
    Explanations

    references to career experience and professional background

    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
    ábado
    -0.07
    insk
    -0.07
    opes
    -0.06
     WTF
    -0.06
    EZ
    -0.06
    lated
    -0.06
    icide
    -0.06
    legen
    -0.06
     preset
    -0.06
    rone
    -0.06
    POSITIVE LOGITS
    Previous
    0.07
    .synthetic
    0.07
    ç¥
    0.07
    Prior
    0.06
     Prior
    0.06
    ossier
    0.06
     зн
    0.06
    VIOUS
    0.06
     Previous
    0.06
     career
    0.06
    Activations Density 0.035%

    No Known Activations