© 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. 22-LLAMASCOPE-RES-131K
    11. 4218
    Prev
    Next
    INDEX
    Explanations

    references to government officials and their titles

    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
     Shannon
    -0.06
    argar
    -0.06
    貨
    -0.06
     Maher
    -0.06
    gerald
    -0.06
    ndo
    -0.06
    poser
    -0.06
     ÅŁer
    -0.06
     Hass
    -0.06
    ÑĢÑĥн
    -0.06
    POSITIVE LOGITS
    ial
    0.07
    iali
    0.07
     Secretary
    0.07
    hic
    0.07
    minster
    0.07
    contrib
    0.07
    份
    0.07
    iske
    0.07
    ially
    0.07
     chatte
    0.06
    Activations Density 0.003%

    No Known Activations