© 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. 5-LLAMASCOPE-RES-131K
    11. 125450
    Prev
    Next
    INDEX
    Explanations

    instances of mathematical constructs and relationships involving space and graphs

    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
    overy
    -0.07
    emd
    -0.07
    istically
    -0.07
    ertas
    -0.06
    á»ĥn
    -0.06
     اÙĦاتØŃاد
    -0.06
    еÑĢаÑĤоÑĢ
    -0.06
    alat
    -0.06
    686
    -0.06
     BaseEntity
    -0.06
    POSITIVE LOGITS
     puls
    0.07
    kova
    0.07
    pulse
    0.07
     Pulse
    0.07
     pulse
    0.07
    quam
    0.06
    zhou
    0.06
    uls
    0.06
    Ä©a
    0.06
    umbo
    0.06
    Activations Density 0.024%

    No Known Activations