© 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. 106568
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Posted" indicating when content was shared or published

    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
    åĭ¢
    -0.07
    Specifier
    -0.07
     æĤ
    -0.07
    że
    -0.07
    atsapp
    -0.06
    isse
    -0.06
    moon
    -0.06
     Chall
    -0.06
    edException
    -0.06
    prints
    -0.06
    POSITIVE LOGITS
    udded
    0.07
    ιδ
    0.06
    licken
    0.06
    Ñĩи
    0.06
     éĴ
    0.06
     cds
    0.06
    udy
    0.06
    çľ¾
    0.06
     Orchard
    0.06
    orado
    0.06
    Activations Density 0.006%

    No Known Activations