© 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. 77068
    Prev
    Next
    INDEX
    Explanations

    references to the concept of commemoration or observance related to mothers

    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
    197
    -0.07
    198
    -0.07
     yür
    -0.07
     Martial
    -0.07
     shit
    -0.07
    cock
    -0.06
    ancode
    -0.06
    ragen
    -0.06
    181
    -0.06
     Marin
    -0.06
    POSITIVE LOGITS
    atorium
    0.08
    ÙĬÙĩ
    0.07
    tero
    0.07
     Olsen
    0.06
    atore
    0.06
     Novel
    0.06
    ippy
    0.06
     novel
    0.06
     titan
    0.06
     copyrighted
    0.06
    Activations Density 0.019%

    No Known Activations