© 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. 87582
    Prev
    Next
    INDEX
    Explanations

    timestamps and references to comments or replies in a conversation

    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
    ³
    -0.06
    artz
    -0.06
    Ñīи
    -0.05
     Cole
    -0.05
    ace
    -0.05
    ADS
    -0.05
    обÑĢаз
    -0.05
     ÑģÑĤек
    -0.05
    266
    -0.05
    817
    -0.05
    POSITIVE LOGITS
     thoughts
    0.12
     Thoughts
    0.11
    thought
    0.10
     thinking
    0.10
     Thinking
    0.10
    thinking
    0.10
     thought
    0.10
    Thought
    0.09
     thinks
    0.09
    Thinking
    0.09
    Activations Density 0.005%

    No Known Activations