© 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. 86259
    Prev
    Next
    INDEX
    Explanations

    terms related to lightness or a light-hearted tone

    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
    ean
    -0.06
    Ŀ
    -0.06
    am
    -0.06
    imensional
    -0.06
     Baker
    -0.06
     Rings
    -0.06
    ụ
    -0.06
     kans
    -0.05
     Stars
    -0.05
    oyal
    -0.05
    POSITIVE LOGITS
    ening
    0.10
    /light
    0.10
    weights
    0.10
    -weight
    0.10
    ened
    0.09
    -duty
    0.09
    (light
    0.09
    weigh
    0.09
    NING
    0.09
    enment
    0.09
    Activations Density 0.022%

    No Known Activations