© 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 EvalsExportsinterp-engineNEWAPI 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. 73194
    Prev
    Next
    INDEX
    Explanations

    terms related to economic impacts and resource allocation

    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
    erah
    -0.07
    ismet
    -0.07
    ellan
    -0.07
    aml
    -0.07
    omap
    -0.07
    ÑĩеÑĢ
    -0.07
    iani
    -0.07
    654
    -0.06
    arra
    -0.06
    kov
    -0.06
    POSITIVE LOGITS
     than
    0.24
    than
    0.21
     THAN
    0.19
    -than
    0.18
     Than
    0.18
    _than
    0.18
    Than
    0.17
     niż
    0.14
     än
    0.12
     než
    0.12
    Activations Density 0.062%

    No Known Activations