© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127722
    Prev
    Next
    INDEX
    Explanations

    phrases related to cancer detection and prevention

    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
    929
    -0.06
    clin
    -0.06
    ovich
    -0.06
    utch
    -0.06
    ader
    -0.06
     antioxid
    -0.06
    ainer
    -0.06
    AINER
    -0.06
    º
    -0.05
    colour
    -0.05
    POSITIVE LOGITS
     treatment
    0.08
     intervention
    0.07
    iao
    0.07
    .MixedReality
    0.07
    attery
    0.07
    untu
    0.07
    itez
    0.07
     meilleurs
    0.07
     chances
    0.07
     treatments
    0.07
    Activations Density 0.010%

    No Known Activations