Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5208
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and sentiments

    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
    ertino
    -0.10
     ,↵↵
    -0.07
    uyết
    -0.07
    ambio
    -0.07
     !↵↵
    -0.07
    elib
    -0.06
     _↵↵
    -0.06
    ampion
    -0.06
    ozilla
    -0.06
    //===
    -0.06
    POSITIVE LOGITS
     ha
    0.15
     haha
    0.13
     LOL
    0.13
     lol
    0.13
    lol
    0.12
    ha
    0.12
     Ha
    0.11
    Ha
    0.10
     HA
    0.10
     Lol
    0.10
    Activations Density 0.554%

    No Known Activations