© 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. 90341
    Prev
    Next
    INDEX
    Explanations

    terms related to charitable giving and donations

    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
    XPath
    -0.06
    plier
    -0.06
    fte
    -0.06
    kate
    -0.06
    iban
    -0.06
     pay
    -0.06
    frey
    -0.06
    gua
    -0.06
     cat
    -0.06
    enton
    -0.06
    POSITIVE LOGITS
     uch
    0.07
    ÂŃn
    0.07
     phy
    0.06
    pus
    0.06
    ÑĢоÑģ
    0.06
    phy
    0.06
    imar
    0.06
    ,âĢ¦↵↵
    0.06
    PLEX
    0.06
     («
    0.06
    Activations Density 0.001%

    No Known Activations