Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96011
    Prev
    Next
    INDEX
    Explanations

    names and titles of medical professionals

    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
    perator
    -0.08
    enser
    -0.08
    ény
    -0.08
    apanese
    -0.08
    gaard
    -0.07
    sembly
    -0.07
    ADE
    -0.07
    alace
    -0.07
    ance
    -0.07
    ethoven
    -0.07
    POSITIVE LOGITS
     Tir
    0.06
     Kil
    0.06
     Billing
    0.06
    ãĤº
    0.06
     â̦↵↵
    0.05
    ë§ī
    0.05
    anity
    0.05
     McG
    0.05
     Ordered
    0.05
    VR
    0.05
    Activations Density 0.009%

    No Known Activations