© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97710
    Prev
    Next
    INDEX
    Explanations

    terms related to earthquakes and seismic activity

    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
    apore
    -0.07
    Ngh
    -0.07
    绩
    -0.07
    stay
    -0.06
    åĬŀçIJĨ
    -0.06
     flyer
    -0.06
    æ¤įçī©
    -0.06
    dater
    -0.06
    _CY
    -0.06
    ×ķ
    -0.06
    POSITIVE LOGITS
    Äħż
    0.07
    pr
    0.07
    /ts
    0.06
    -translate
    0.06
    cj
    0.06
    erk
    0.06
     ÐĵÑĢи
    0.06
    ì´Į
    0.06
    ĩ
    0.05
    -rel
    0.05
    Activations Density 0.007%

    No Known Activations