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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 55923
    Prev
    Next
    INDEX
    Explanations

    events and activities related to public gatherings and community engagement

    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
     Leban
    -0.07
    à¸ģà¸ķ
    -0.07
    abal
    -0.06
    aliz
    -0.06
     recruit
    -0.06
    pard
    -0.06
    apur
    -0.06
    ivy
    -0.06
     Tür
    -0.06
    ouz
    -0.06
    POSITIVE LOGITS
    clc
    0.07
    Ïħγ
    0.07
    ibase
    0.07
    .Microsoft
    0.07
    addtogroup
    0.06
    ages
    0.06
    gesi
    0.06
    oplan
    0.06
    wie
    0.06
    uge
    0.06
    Activations Density 0.019%

    No Known Activations