© 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. 41765
    Prev
    Next
    INDEX
    Explanations

    comparisons involving less than or equal to

    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
     ฿
    -0.07
    orem
    -0.07
     nig
    -0.07
    ebi
    -0.06
    mund
    -0.06
    ÇIJ
    -0.06
    orde
    -0.06
    nowledge
    -0.06
     ::=
    -0.06
    isse
    -0.06
    POSITIVE LOGITS
    ched
    0.08
    chers
    0.07
    ching
    0.07
    mo
    0.06
    å±ĭ
    0.06
    _sensitive
    0.06
    999
    0.06
    nds
    0.06
    leted
    0.06
    amp
    0.06
    Activations Density 0.016%

    No Known Activations