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

    Neuronpedia

    Jacobian LensNEW
    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. 60720
    Prev
    Next
    INDEX
    Explanations

    phrases related to consent and agreement, particularly in terms of terms and conditions

    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
    qua
    -0.08
     spect
    -0.08
    ç¦
    -0.07
    æģ¯
    -0.07
    оÐ
    -0.07
     desn
    -0.07
    apo
    -0.07
    .Microsoft
    -0.07
    bart
    -0.06
    quit
    -0.06
    POSITIVE LOGITS
    869
    0.06
    ilater
    0.06
    lamaz
    0.06
    ilogy
    0.06
     Petty
    0.06
    itar
    0.06
     to
    0.06
     bu
    0.05
     RB
    0.05
    atively
    0.05
    Activations Density 0.001%

    No Known Activations