© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 61423
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the cultural significance or history of specific subjects

    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
    ãģ°ãģĭãĤĬ
    -0.07
    ейн
    -0.07
     æĸ¹
    -0.07
    ãİ
    -0.07
    utch
    -0.07
    _exports
    -0.06
    eway
    -0.06
    /tiny
    -0.06
     die
    -0.06
    istrovstvÃŃ
    -0.06
    POSITIVE LOGITS
    oment
    0.07
    632
    0.07
    ohon
    0.06
     Auch
    0.06
    AKE
    0.06
    lect
    0.06
    esco
    0.06
    ifu
    0.06
    ings
    0.06
     Higgins
    0.06
    Activations Density 0.051%

    No Known Activations