© 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. 89183
    Prev
    Next
    INDEX
    Explanations

    references to professional transitions and changes in occupation

    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
     Robinson
    -0.07
     Tarif
    -0.06
    utsch
    -0.06
    indsight
    -0.06
     kök
    -0.06
     Weak
    -0.06
     Stall
    -0.06
    å¿ł
    -0.06
    än
    -0.06
    weak
    -0.06
    POSITIVE LOGITS
     public
    0.10
     mainstream
    0.08
     actively
    0.08
     active
    0.08
     retirement
    0.08
    public
    0.07
    ymm
    0.07
     publicly
    0.07
    endale
    0.07
    Active
    0.07
    Activations Density 0.013%

    No Known Activations