© 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. 126969
    Prev
    Next
    INDEX
    Explanations

    terms associated with political and legal actions

    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
    âĢį
    -0.07
     fucked
    -0.07
     shitty
    -0.06
     rumours
    -0.06
    EMENT
    -0.06
     hoá
    -0.06
     &
    -0.06
    024
    -0.06
     Fucking
    -0.06
    âĢ¦↵↵
    -0.06
    POSITIVE LOGITS
    WND
    0.11
    erif
    0.07
    ÙħاÙĦ
    0.07
     sana
    0.07
     اÙĦرÙħزÙĬØ©
    0.07
     sı
    0.07
    ADX
    0.07
     ÙĨÙħاÛĮØ´
    0.06
    ãĥ£
    0.06
    ugi
    0.06
    Activations Density 0.001%

    No Known Activations