© 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. 4758
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS elements, specifically related to table structures and styles

    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
    oze
    -0.08
    387
    -0.07
     molec
    -0.07
    ãĥ³ãĥIJ
    -0.07
    421
    -0.07
    itia
    -0.06
     MÃ¼ÅŁ
    -0.06
    ordion
    -0.06
    imap
    -0.06
    654
    -0.06
    POSITIVE LOGITS
    çĵľ
    0.08
    screens
    0.07
    æ¸Ī
    0.07
    oggler
    0.06
     ethers
    0.06
    ospace
    0.06
    rup
    0.06
    cola
    0.06
    Align
    0.06
    _CELL
    0.06
    Activations Density 0.018%

    No Known Activations