© 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. 42426
    Prev
    Next
    INDEX
    Explanations

    architectural styles and descriptors related to design and aesthetics

    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
    ilar
    -0.06
    ãĥ³ãĤ¯
    -0.06
    licit
    -0.06
    (s
    -0.06
     plá
    -0.06
    tep
    -0.06
     Kut
    -0.05
     ctor
    -0.05
    endale
    -0.05
    erson
    -0.05
    POSITIVE LOGITS
    -style
    0.14
     style
    0.13
    -leaning
    0.11
     styled
    0.10
    -inspired
    0.10
     STYLE
    0.10
    -looking
    0.10
    style
    0.10
     Style
    0.10
    -esque
    0.09
    Activations Density 0.018%

    No Known Activations