© 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. 104839
    Prev
    Next
    INDEX
    Explanations

    references to refunds and financial compensation

    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
    clc
    -0.07
    Delegate
    -0.07
     обÑĢаÑĤ
    -0.07
    .Ui
    -0.07
    .createFrom
    -0.07
    ÙĨاء
    -0.06
    axy
    -0.06
     пÑĢиÑĤ
    -0.06
     recess
    -0.06
    asts
    -0.06
    POSITIVE LOGITS
     customer
    0.07
    Locator
    0.07
     promised
    0.06
     resolution
    0.06
     Trace
    0.06
    åĵģ
    0.06
     Customer
    0.06
     promising
    0.06
     inconvenience
    0.06
    onus
    0.06
    Activations Density 0.015%

    No Known Activations