© 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. 72000
    Prev
    Next
    INDEX
    Explanations

    moments of close competition in sports

    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
    PA
    -0.08
    emer
    -0.07
     Voll
    -0.07
    esModule
    -0.07
    iminal
    -0.07
    lak
    -0.07
    ãĥĨãĥ«
    -0.07
    ÙĬار
    -0.07
    âĻª
    -0.07
    allen
    -0.07
    POSITIVE LOGITS
     throughout
    0.09
    brief
    0.08
     Throughout
    0.07
     lead
    0.07
     Ñģобой
    0.06
    é¢Ĩ
    0.06
    uky
    0.06
    ingleton
    0.06
    Throughout
    0.06
     during
    0.06
    Activations Density 0.004%

    No Known Activations