Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44269
    Prev
    Next
    INDEX
    Explanations

    phrases related to career preparation and job market skills

    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
    /Instruction
    -0.09
    ednou
    -0.07
    lej
    -0.07
     sÃŃd
    -0.07
    ilos
    -0.07
     trú
    -0.06
    enie
    -0.06
    quil
    -0.06
    ulty
    -0.06
    organisation
    -0.06
    POSITIVE LOGITS
     careers
    0.13
     post
    0.12
     lives
    0.11
     futures
    0.11
     future
    0.11
     professions
    0.10
     employment
    0.10
     occupations
    0.10
     entry
    0.10
     tomorrow
    0.10
    Activations Density 0.054%

    No Known Activations