© 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. 59070
    Prev
    Next
    INDEX
    Explanations

    words related to various forms of creative expression, particularly in film and literature

    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
    tings
    -0.07
    kinson
    -0.07
    icular
    -0.07
    anson
    -0.07
    lett
    -0.07
    ÑĢаж
    -0.07
    yla
    -0.07
    ÙħاÙĨÛĮ
    -0.07
    sword
    -0.06
    ustin
    -0.06
    POSITIVE LOGITS
    naire
    0.21
    naires
    0.18
    ally
    0.18
    ality
    0.17
    ary
    0.17
    nement
    0.16
    nal
    0.15
    als
    0.15
    nel
    0.15
    aries
    0.13
    Activations Density 0.118%

    No Known Activations