© 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. 126927
    Prev
    Next
    INDEX
    Explanations

    words related to medical terminology or concepts

    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
     flash
    -0.06
     desp
    -0.06
    590
    -0.05
     delic
    -0.05
     Prest
    -0.05
     unpack
    -0.05
     precisely
    -0.05
     bla
    -0.05
    -0.05
     comput
    -0.05
    POSITIVE LOGITS
    BERS
    0.08
    ndon
    0.07
    ë¹ĦìķĦ
    0.07
    tdown
    0.07
    WEEN
    0.07
    okit
    0.07
    posables
    0.07
    ahir
    0.07
    PEAT
    0.07
    fte
    0.07
    Activations Density 0.000%

    No Known Activations