© 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. 93904
    Prev
    Next
    INDEX
    Explanations

    references to historical events and relative dates

    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
    ilateral
    -0.06
    qua
    -0.06
     unlike
    -0.06
    atten
    -0.06
    abar
    -0.06
    lef
    -0.06
    201
    -0.06
     karak
    -0.06
     Fibonacci
    -0.06
    anka
    -0.06
    POSITIVE LOGITS
    193
    0.11
    194
    0.09
    192
    0.09
    ï¼ĪæĺŃåĴĮ
    0.07
    ëħĦ
    0.07
    IGIN
    0.07
     WW
    0.07
    URLRequest
    0.07
     vintage
    0.07
    saldo
    0.06
    Activations Density 0.039%

    No Known Activations