© 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. 17-LLAMASCOPE-RES-131K
    11. 39072
    Prev
    Next
    INDEX
    Explanations

    time-related expressions, particularly focusing on the word "year"

    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
    æ°¸ä¹ħ
    -0.06
    oje
    -0.06
    Msp
    -0.06
    icter
    -0.06
     Vampire
    -0.06
    okane
    -0.06
    akedown
    -0.06
    jev
    -0.06
     Gravity
    -0.06
    izik
    -0.06
    POSITIVE LOGITS
    fty
    0.07
    ibe
    0.06
    鹿
    0.06
    ît
    0.06
    /if
    0.06
    YLE
    0.06
    earing
    0.06
     there
    0.06
    imd
    0.05
    OX
    0.05
    Activations Density 0.023%

    No Known Activations