© 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. 29425
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic conditions and financial burdens

    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
    oÅĻ
    -0.08
    oq
    -0.07
    žÃŃ
    -0.06
    Äįe
    -0.06
     bá»ķ
    -0.06
    ednou
    -0.06
    oin
    -0.06
    _DECL
    -0.06
    UAGE
    -0.06
    (.)
    -0.06
    POSITIVE LOGITS
    know
    0.08
     being
    0.08
     knowing
    0.07
     having
    0.07
    edy
    0.07
     KNOW
    0.06
    inel
    0.06
    estar
    0.06
     hindsight
    0.06
    851
    0.06
    Activations Density 0.028%

    No Known Activations