© 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. 82061
    Prev
    Next
    INDEX
    Explanations

    references to historical figures and events related to political leadership

    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
    kova
    -0.08
     Damen
    -0.07
    uci
    -0.07
    prov
    -0.07
    arius
    -0.07
    ULA
    -0.07
     Melbourne
    -0.06
    ège
    -0.06
     Logic
    -0.06
    ignon
    -0.06
    POSITIVE LOGITS
     Roosevelt
    0.08
    velt
    0.08
     speech
    0.07
    Speech
    0.07
     speeches
    0.07
     Speech
    0.07
    Pres
    0.07
     Flush
    0.06
    bounding
    0.06
     NY
    0.06
    Activations Density 0.004%

    No Known Activations