© 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. 129684
    Prev
    Next
    INDEX
    Explanations

    phrases related to coming up with ideas or strategies

    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
    iam
    -0.06
     collective
    -0.06
    erez
    -0.06
    854
    -0.06
    enschaft
    -0.06
    É
    -0.06
    adio
    -0.06
     Lauderdale
    -0.06
    817
    -0.06
    ember
    -0.06
    POSITIVE LOGITS
     himself
    0.08
     whenever
    0.07
    áºł
    0.07
    머ëĭĪ
    0.06
    bard
    0.06
    ská
    0.06
    Whenever
    0.06
     CONSEQUENTIAL
    0.06
    жÑĥ
    0.06
    jÅ¡ÃŃ
    0.06
    Activations Density 0.000%

    No Known Activations