© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15717
    Prev
    Next
    INDEX
    Explanations

    references to historical and geographical contexts related to Cape Town

    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
     Brill
    -0.07
    amax
    -0.07
    neas
    -0.07
     æº
    -0.07
    itm
    -0.07
    anship
    -0.07
    á»ijc
    -0.07
    acre
    -0.07
    piler
    -0.06
     zad
    -0.06
    POSITIVE LOGITS
     Mandela
    0.13
     African
    0.10
     Nelson
    0.08
     ANC
    0.08
     Africa
    0.07
     Africans
    0.07
     Gandhi
    0.07
    Africa
    0.07
     african
    0.07
     Nd
    0.06
    Activations Density 0.004%

    No Known Activations