© 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. 124170
    Prev
    Next
    INDEX
    Explanations

    references to iconic sporting events and pivotal moments in sports history

    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
    rello
    -0.07
    .ManyToMany
    -0.06
     Freund
    -0.06
    ereum
    -0.06
    æķ
    -0.06
     newest
    -0.06
    amedi
    -0.06
    wers
    -0.06
    aca
    -0.06
    .firebaseapp
    -0.06
    POSITIVE LOGITS
     famously
    0.11
     memorable
    0.08
     ann
    0.08
     iconic
    0.08
     legendary
    0.07
     remembers
    0.07
     infamous
    0.07
    UTERS
    0.07
    mem
    0.07
    198
    0.07
    Activations Density 0.034%

    No Known Activations