© 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. 17-LLAMASCOPE-RES-131K
    11. 93515
    Prev
    Next
    INDEX
    Explanations

    information related to employment and job changes

    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
     Roose
    -0.08
    stu
    -0.06
    ahoma
    -0.06
    orsche
    -0.06
     Sad
    -0.06
    oÄį
    -0.06
     action
    -0.06
    uida
    -0.06
     somewhere
    -0.06
     unm
    -0.06
    POSITIVE LOGITS
     Initially
    0.08
     initially
    0.08
    Initially
    0.08
    plant
    0.07
     plant
    0.07
    lik
    0.07
     Imported
    0.07
    oz
    0.07
    .NewRequest
    0.06
    ê·¼
    0.06
    Activations Density 0.004%

    No Known Activations