© 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. 80390
    Prev
    Next
    INDEX
    Explanations

    statistical performances and achievements 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
    bjerg
    -0.09
    idata
    -0.08
    dge
    -0.07
    swick
    -0.07
    ÃĸL
    -0.07
    rink
    -0.07
    pulse
    -0.06
    isposable
    -0.06
    py
    -0.06
    AKE
    -0.06
    POSITIVE LOGITS
    eba
    0.06
     block
    0.06
    agements
    0.06
     gated
    0.05
     DNA
    0.05
    icts
    0.05
     bueno
    0.05
     immobil
    0.05
     recovered
    0.05
    OfType
    0.05
    Activations Density 0.003%

    No Known Activations