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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82487
    Prev
    Next
    INDEX
    Explanations

    instances of emotional or dramatic events occurring between characters

    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
     mess
    -0.07
    airy
    -0.07
    mach
    -0.06
    blink
    -0.06
    ucky
    -0.06
    asty
    -0.06
    iw
    -0.06
    uckle
    -0.06
    ingle
    -0.06
    Ïģκ
    -0.06
    POSITIVE LOGITS
     ended
    0.08
    leigh
    0.07
    éĢĶ
    0.07
     Vect
    0.07
    æľŁéĹ´
    0.06
     Ended
    0.06
     ÑģлÑĥÑĩай
    0.06
     discovers
    0.06
     discovered
    0.06
     resulted
    0.06
    Activations Density 0.042%

    No Known Activations