© 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. 4216
    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
    iesel
    -0.07
    éis
    -0.07
    gba
    -0.07
    irim
    -0.07
    411
    -0.07
    partials
    -0.07
    inged
    -0.06
    uffix
    -0.06
    neider
    -0.06
     Ñģобой
    -0.06
    POSITIVE LOGITS
    mes
    0.06
    bie
    0.06
    ä¹Ī
    0.06
    ope
    0.06
    s
    0.06
     spectator
    0.06
    une
    0.06
    co
    0.06
    inger
    0.05
    URN
    0.05
    Activations Density 0.042%

    No Known Activations