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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 128690
    Prev
    Next
    INDEX
    Explanations

    references to cities and their significance

    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
    irit
    -0.08
    гал
    -0.08
    Ø´Ùħ
    -0.07
     Zaman
    -0.07
    .Selenium
    -0.07
    ä½įæĸ¼
    -0.07
    омен
    -0.07
    itta
    -0.07
    ëĭĪëĭ¤
    -0.06
    italic
    -0.06
    POSITIVE LOGITS
     host
    0.11
     hosts
    0.10
     hosting
    0.09
    host
    0.08
    hosts
    0.07
    Host
    0.07
    imeo
    0.07
     Host
    0.07
     sede
    0.07
     headquarters
    0.07
    Activations Density 0.014%

    No Known Activations