© 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. 15-LLAMASCOPE-RES-131K
    11. 644
    Prev
    Next
    INDEX
    Explanations

    descriptions of personal transformation and inner conflict

    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
    abox
    -0.07
    stav
    -0.07
    okino
    -0.07
    ASIC
    -0.07
    ewater
    -0.07
    æ¢
    -0.07
    ês
    -0.07
    еÑħ
    -0.07
    á»ĩ
    -0.07
    olas
    -0.07
    POSITIVE LOGITS
     suddenly
    0.09
     transformed
    0.09
     transformation
    0.08
     transform
    0.08
     reverted
    0.07
    transform
    0.07
     transforms
    0.07
     demeanor
    0.07
     Suddenly
    0.07
     persona
    0.07
    Activations Density 0.062%

    No Known Activations