© 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. 74712
    Prev
    Next
    INDEX
    Explanations

    references to academic journals, specifically in the medical field

    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
    çļ
    -0.06
     é¢
    -0.06
     pun
    -0.06
    елов
    -0.06
    umps
    -0.06
     Persons
    -0.06
     Norman
    -0.06
    pun
    -0.06
    FromString
    -0.05
     Bare
    -0.05
    POSITIVE LOGITS
    ctp
    0.07
    263
    0.06
     CType
    0.06
     vaz
    0.06
    zing
    0.06
    axy
    0.06
    بÙĬر
    0.06
    Soup
    0.06
    akash
    0.06
    Ñģклад
    0.06
    Activations Density 0.002%

    No Known Activations