© 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. 9-LLAMASCOPE-RES-131K
    11. 94619
    Prev
    Next
    INDEX
    Explanations

    geographical and political references related to Africa and its historical context

    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
    KY
    -0.06
     unb
    -0.06
    unei
    -0.06
     sight
    -0.06
     myth
    -0.06
     quant
    -0.06
    antan
    -0.06
    BUR
    -0.06
    esson
    -0.06
    ucc
    -0.05
    POSITIVE LOGITS
    ois
    0.08
    ÄĻd
    0.07
    xab
    0.07
    ãĥ¼ãĤ¯
    0.07
    iliation
    0.06
    inine
    0.06
    sse
    0.06
    /run
    0.06
     fold
    0.06
    achat
    0.06
    Activations Density 0.020%

    No Known Activations