© 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. 95141
    Prev
    Next
    INDEX
    Explanations

    mentions of pet health issues and veterinary experiences

    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
    agues
    -0.07
    finger
    -0.07
     hút
    -0.07
    voy
    -0.07
    WithDuration
    -0.07
     célib
    -0.07
    chaft
    -0.06
    @email
    -0.06
    -src
    -0.06
    isko
    -0.06
    POSITIVE LOGITS
    sp
    0.07
    ì©
    0.06
    esta
    0.06
    ãĥ¼ãĤ¯
    0.06
     Veterinary
    0.06
     Madd
    0.06
     æ±
    0.06
    æŁı
    0.06
     Appointment
    0.06
    pur
    0.06
    Activations Density 0.004%

    No Known Activations