© 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. 107374
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to job application processes and requirements

    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
    host
    -0.07
    hos
    -0.06
     poll
    -0.06
    nen
    -0.06
    vä
    -0.06
    onen
    -0.06
     POLL
    -0.06
    oriously
    -0.06
     PARTY
    -0.06
     polls
    -0.06
    POSITIVE LOGITS
     vacancy
    0.08
     HR
    0.07
     resume
    0.07
     Job
    0.07
    HR
    0.07
     Cv
    0.07
    _POSITION
    0.06
    ENGINE
    0.06
    ools
    0.06
    Job
    0.06
    Activations Density 0.013%

    No Known Activations