© 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. 4571
    Prev
    Next
    INDEX
    Explanations

    references to various holidays and festive celebrations

    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
    lical
    -0.06
     h
    -0.06
    hort
    -0.06
     tact
    -0.06
     tang
    -0.05
    mentor
    -0.05
    .jdesktop
    -0.05
    .SetValue
    -0.05
     chatter
    -0.05
     getElement
    -0.05
    POSITIVE LOGITS
    uf
    0.08
     edition
    0.08
    242
    0.08
    ÐķС
    0.07
    -themed
    0.07
     pul
    0.07
    ilha
    0.07
    ë³´ëĤ´ê¸°
    0.07
    ÏĦÏģ
    0.07
    acyj
    0.07
    Activations Density 0.018%

    No Known Activations