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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 857
    Prev
    Next
    INDEX
    Explanations

    phrases related to job eligibility and application processes

    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
    oup
    -0.07
    aps
    -0.06
    igo
    -0.06
    ague
    -0.06
    asher
    -0.06
    ilot
    -0.06
    ubi
    -0.06
    acam
    -0.06
    U
    -0.06
    ilon
    -0.06
    POSITIVE LOGITS
    릿
    0.07
    ednou
    0.07
    kanı
    0.07
     GOODMAN
    0.07
    isay
    0.07
    ırak
    0.07
    755
    0.07
    allen
    0.07
    CLUDING
    0.07
    ument
    0.06
    Activations Density 0.015%

    No Known Activations