© 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. 120810
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional phrases that indicate logical relationships or conclusions

    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
    kart
    -0.07
    'gc
    -0.07
    guard
    -0.07
    702
    -0.07
    isÃŃ
    -0.07
    473
    -0.07
    vat
    -0.06
     scn
    -0.06
    omap
    -0.06
    ãĥ³ãĥĩ
    -0.06
    POSITIVE LOGITS
    forth
    0.08
     latter
    0.08
    ãģ£ãģ¨
    0.07
    że
    0.07
    ï¸ı
    0.07
    ever
    0.07
    peria
    0.06
    eks
    0.06
    AYS
    0.06
    çĩ
    0.06
    Activations Density 0.024%

    No Known Activations