© 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. 56076
    Prev
    Next
    INDEX
    Explanations

    parentheses in the text

    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
    793
    -0.07
    wij
    -0.07
    manent
    -0.07
    adan
    -0.07
    803
    -0.06
    Genre
    -0.06
    ovich
    -0.06
    stile
    -0.06
    rock
    -0.06
    ä¼ģ
    -0.06
    POSITIVE LOGITS
    cta
    0.06
    ounc
    0.06
     Bare
    0.06
    ην
    0.06
    õ
    0.06
    ujet
    0.06
    amba
    0.06
     ëĭ¤ìļ´ë°Ľê¸°
    0.06
    hta
    0.06
     My
    0.06
    Activations Density 0.006%

    No Known Activations