© 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. 22-LLAMASCOPE-RES-131K
    11. 4102
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Caesar" or related variations

    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
    го
    -0.08
    ÏĦιν
    -0.07
    auge
    -0.07
    phant
    -0.06
    burgh
    -0.06
    agnosis
    -0.06
    addtogroup
    -0.06
    bsite
    -0.06
    heid
    -0.06
    Generic
    -0.06
    POSITIVE LOGITS
    UTION
    0.09
    ution
    0.09
    esar
    0.08
     khúc
    0.08
    /ca
    0.08
     Ca
    0.07
     ca
    0.07
    ulk
    0.07
    iazza
    0.07
    (ca
    0.07
    Activations Density 0.011%

    No Known Activations