© 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. 61436
    Prev
    Next
    INDEX
    Explanations

    references to military actions and conflicts involving specific groups

    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
     ún
    -0.08
    thers
    -0.06
    aders
    -0.06
    ');?>"
    -0.06
    .ShouldBe
    -0.06
    prot
    -0.06
     .*
    -0.06
    ervlet
    -0.06
    /as
    -0.06
     sheer
    -0.06
    POSITIVE LOGITS
    ullo
    0.07
    inton
    0.07
    ìłĦìĹIJ
    0.06
     Courtesy
    0.06
     \`
    0.06
    krom
    0.06
    (AP
    0.06
    CompleteListener
    0.06
    Dump
    0.06
     ActionController
    0.06
    Activations Density 0.012%

    No Known Activations