© 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. 126380
    Prev
    Next
    INDEX
    Explanations

    elements related to military or conflict themes

    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
    جÙĪ
    -0.07
    buz
    -0.07
     Obrázky
    -0.07
    anyak
    -0.07
    еÑĢжав
    -0.07
    ayo
    -0.06
    amura
    -0.06
    ateria
    -0.06
    оÑĤе
    -0.06
    iele
    -0.06
    POSITIVE LOGITS
     Bott
    0.07
    ngrx
    0.07
     which
    0.07
     Erd
    0.06
    æµľ
    0.06
     Lesser
    0.06
     tongue
    0.06
    MLS
    0.06
    idon
    0.06
    ÑĪкÑĥ
    0.06
    Activations Density 0.041%

    No Known Activations