© 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. 18137
    Prev
    Next
    INDEX
    Explanations

    words related to health, specifically medical diagnoses and their implications

    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
     Stitch
    -0.06
    anni
    -0.06
    uda
    -0.06
     Ga
    -0.06
    عدد
    -0.06
    uj
    -0.06
    reon
    -0.05
     La
    -0.05
     Ple
    -0.05
     Buen
    -0.05
    POSITIVE LOGITS
     Speech
    0.10
    peech
    0.10
    Speech
    0.10
     speech
    0.09
    ieber
    0.09
    speech
    0.08
    ousel
    0.08
    ffset
    0.07
    mounted
    0.07
    plist
    0.07
    Activations Density 0.001%

    No Known Activations