© 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. 40417
    Prev
    Next
    INDEX
    Explanations

    phrases indicating preference or comparison

    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
    folio
    -0.07
    pedia
    -0.07
    .dm
    -0.07
    é¡į
    -0.07
    í
    -0.07
    duk
    -0.07
    ridge
    -0.06
    éĹ²
    -0.06
     詳細
    -0.06
    á»IJ
    -0.06
    POSITIVE LOGITS
    /or
    0.08
     bar
    0.06
    lando
    0.06
    ovel
    0.05
    ashboard
    0.05
    tml
    0.05
    ĥ
    0.05
     strictly
    0.05
    ld
    0.05
    ź
    0.05
    Activations Density 0.011%

    No Known Activations