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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 88960
    Prev
    Next
    INDEX
    Explanations

    themes and discussions surrounding conflict and morality in narratives

    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
    ng
    -0.07
    ampo
    -0.07
    ill
    -0.06
     (?)
    -0.06
    avenport
    -0.06
     Pon
    -0.06
    ä¹Ī
    -0.06
     irgend
    -0.06
     (?
    -0.06
    ona
    -0.06
    POSITIVE LOGITS
     ÙĪÙħا
    0.08
    ãĤµãĥ¼
    0.08
    ØŁ
    0.07
    lops
    0.07
    íĸĪê³ł
    0.07
    ÅĻiv
    0.07
    ellan
    0.07
    ?↵↵↵↵
    0.07
    åij¢
    0.07
    ãĤ·ãĥ¼
    0.07
    Activations Density 0.055%

    No Known Activations