© 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. 15-LLAMASCOPE-RES-131K
    11. 88155
    Prev
    Next
    INDEX
    Explanations

    HTML tags and code structure elements

    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
    letter
    -0.06
    èķī
    -0.06
    er
    -0.06
    inar
    -0.06
    aho
    -0.06
    iter
    -0.06
    haus
    -0.05
    azel
    -0.05
    iterate
    -0.05
    ertility
    -0.05
    POSITIVE LOGITS
    695
    0.07
    Ú¯ÙĪÙĨÙĩ
    0.07
    .componentInstance
    0.07
    pio
    0.07
    º¼
    0.07
    æĤŁ
    0.07
    errat
    0.07
    inalg
    0.06
    رات
    0.06
    adnÃŃ
    0.06
    Activations Density 0.000%

    No Known Activations