© 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. 93915
    Prev
    Next
    INDEX
    Explanations

    discussion of advantages and disadvantages of various systems or processes related to energy and finance

    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
    aeper
    -0.07
    _fitness
    -0.07
    .Gradient
    -0.07
    stro
    -0.07
    esen
    -0.07
    .LoggerFactory
    -0.07
    .GetItem
    -0.07
    ùa
    -0.07
     à¸ģรà¸ģ
    -0.06
    .sendMessage
    -0.06
    POSITIVE LOGITS
     easy
    0.07
     chance
    0.07
     democratic
    0.07
     flexibility
    0.07
    asily
    0.07
     ëĶ°
    0.06
     no
    0.06
    irm
    0.06
     unlike
    0.06
     Heller
    0.06
    Activations Density 0.027%

    No Known Activations