© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 94186
    Prev
    Next
    INDEX
    Explanations

    phrases related to job benefits and compensation packages

    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
    oth
    -0.07
    lap
    -0.06
     Ko
    -0.06
    è®
    -0.05
    une
    -0.05
    azy
    -0.05
    omed
    -0.05
     bern
    -0.05
     present
    -0.05
     moi
    -0.05
    POSITIVE LOGITS
    uran
    0.07
    Ñĥмов
    0.07
    à¤Łà¤ķ
    0.07
    adil
    0.07
     pec
    0.07
    uve
    0.07
    emma
    0.07
    Salary
    0.07
    quam
    0.07
     sır
    0.07
    Activations Density 0.003%

    No Known Activations