© 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 EvalsExportsinterp-engineNEWAPI 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. 86484
    Prev
    Next
    INDEX
    Explanations

    words indicating the state or condition of patients

    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
    AML
    -0.07
     åĨĨ
    -0.07
    -ÑĤо
    -0.07
    Ñħи
    -0.07
    rette
    -0.07
    uggage
    -0.07
    linger
    -0.06
    ayıp
    -0.06
    azar
    -0.06
    ROC
    -0.06
    POSITIVE LOGITS
    able
    0.06
    ữ
    0.06
    aus
    0.06
     walkers
    0.06
    Signed
    0.06
    usic
    0.05
    तम
    0.05
    uhn
    0.05
     able
    0.05
    usc
    0.05
    Activations Density 0.026%

    No Known Activations