Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95937
    Prev
    Next
    INDEX
    Explanations

    references to political tensions and conflicts

    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
    ³
    -0.06
    oha
    -0.06
    570
    -0.06
    inals
    -0.06
    inkel
    -0.06
     Graz
    -0.06
     HomeController
    -0.06
     Cork
    -0.05
     Deferred
    -0.05
     $('[
    -0.05
    POSITIVE LOGITS
    /path
    0.07
    jsp
    0.07
    :UIAlert
    0.07
    bote
    0.07
     whit
    0.07
    avel
    0.07
    antly
    0.06
    bersome
    0.06
    /epl
    0.06
    supported
    0.06
    Activations Density 0.031%

    No Known Activations