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

    Neuronpedia

    Jacobian LensNEW
    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. 82841
    Prev
    Next
    INDEX
    Explanations

    phrases related to retirement planning and financial security

    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
    ENCED
    -0.06
    ForObject
    -0.06
    bable
    -0.06
    quota
    -0.06
     te
    -0.06
    ован
    -0.06
    orp
    -0.06
    gin
    -0.06
    à¸ĵ
    -0.06
    ONUS
    -0.06
    POSITIVE LOGITS
     Pension
    0.08
     retirement
    0.08
     inflation
    0.07
     pension
    0.07
    plan
    0.07
     Social
    0.07
    acz
    0.07
     Retirement
    0.07
     пен
    0.07
     retire
    0.07
    Activations Density 0.005%

    No Known Activations