© 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. 103314
    Prev
    Next
    INDEX
    Explanations

    phrases related to causes, explanations, and outcomes

    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
    æĩ
    -0.07
    yme
    -0.07
     Spin
    -0.07
    zcze
    -0.07
    ÙĪع
    -0.07
    éĢĨ
    -0.07
     Fade
    -0.06
    verity
    -0.06
    emode
    -0.06
    Spin
    -0.06
    POSITIVE LOGITS
     causing
    0.08
     cause
    0.08
     causa
    0.07
     responsible
    0.07
     caused
    0.07
     somehow
    0.07
     causes
    0.07
    cause
    0.07
     Explanation
    0.06
     caus
    0.06
    Activations Density 0.008%

    No Known Activations