© 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. 106190
    Prev
    Next
    INDEX
    Explanations

    references to large bodies of water or metaphorical expressions about movement and change

    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
    eon
    -0.07
    ocio
    -0.07
    енка
    -0.06
    mie
    -0.06
    ature
    -0.06
     dripping
    -0.06
    ruh
    -0.06
    lov
    -0.06
    izzo
    -0.06
    iveness
    -0.06
    POSITIVE LOGITS
     waves
    0.09
     waters
    0.08
    /stream
    0.08
     depths
    0.08
    eres
    0.08
     tide
    0.07
     wave
    0.07
     Waves
    0.07
    /ts
    0.07
    emoc
    0.07
    Activations Density 0.038%

    No Known Activations