© 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. 120588
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives that convey a strong sense of interest or emotion

    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
    508
    -0.07
    507
    -0.07
     chóng
    -0.07
    ikes
    -0.06
    increments
    -0.06
    menin
    -0.06
    509
    -0.06
    orum
    -0.06
    pike
    -0.06
    è¨Ī
    -0.06
    POSITIVE LOGITS
     aspect
    0.12
     aspects
    0.10
     feature
    0.10
     thing
    0.10
     features
    0.09
     part
    0.08
    aspect
    0.08
    features
    0.08
    Aspect
    0.08
    feature
    0.08
    Activations Density 0.019%

    No Known Activations