© 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. 15-LLAMASCOPE-RES-131K
    11. 88966
    Prev
    Next
    INDEX
    Explanations

    conditional statements and advice

    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
    ibur
    -0.06
    ahn
    -0.06
    olland
    -0.06
    jon
    -0.06
     Nullable
    -0.06
    ahan
    -0.06
    uros
    -0.06
    ipur
    -0.06
    ares
    -0.05
     Kah
    -0.05
    POSITIVE LOGITS
     properly
    0.10
    proper
    0.08
     proper
    0.08
     Proper
    0.08
     carefully
    0.07
     correctly
    0.07
    agna
    0.07
    ngo
    0.07
    inges
    0.07
    reta
    0.07
    Activations Density 0.037%

    No Known Activations