© 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. 16688
    Prev
    Next
    INDEX
    Explanations

    references to high-ranking political and military officials

    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
    iyan
    -0.08
    apor
    -0.08
    주ìĿĺ
    -0.08
    sse
    -0.07
    νι
    -0.07
    gili
    -0.07
    rans
    -0.07
    аÑĢан
    -0.07
    INCREMENT
    -0.07
    adol
    -0.07
    POSITIVE LOGITS
     figures
    0.09
    -level
    0.07
     level
    0.07
     ech
    0.07
     executives
    0.07
    /high
    0.07
     officials
    0.06
     levels
    0.06
    /exec
    0.06
     figure
    0.06
    Activations Density 0.013%

    No Known Activations