© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 26698
    Prev
    Next
    INDEX
    Explanations

    CSS styling attributes related to colors and backgrounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML/CSS color and formatting attributes in web page and document layout code, particularly in table styling contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     RCS
    -0.06
     Bridges
    -0.06
    ese
    -0.06
    VOKE
    -0.06
    εÏģγ
    -0.05
    agh
    -0.05
    .nz
    -0.05
    eller
    -0.05
     tread
    -0.05
     Esk
    -0.05
    POSITIVE LOGITS
    lesia
    0.07
    .gdx
    0.07
    quiv
    0.07
    -UA
    0.07
    verity
    0.07
    ulumi
    0.07
    taire
    0.07
    donnees
    0.06
    ERENCE
    0.06
    avanaugh
    0.06
    Activations Density 0.001%

    No Known Activations