© 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. 93442
    Prev
    Next
    INDEX
    Explanations

    phrases related to hiring practices and candidate evaluations

    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
    дейÑģÑĤв
    -0.08
    nila
    -0.08
    iag
    -0.08
    Insensitive
    -0.08
    _Tis
    -0.07
    UrlParser
    -0.07
    AdapterFactory
    -0.07
     INTERRUPTION
    -0.07
    esModule
    -0.07
    vÃŃc
    -0.07
    POSITIVE LOGITS
     job
    0.08
     applicant
    0.07
     hire
    0.07
     CV
    0.07
     candidate
    0.07
    licant
    0.07
     cv
    0.07
     applicants
    0.07
     fit
    0.07
     resume
    0.07
    Activations Density 0.014%

    No Known Activations