© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 78854
    Prev
    Next
    INDEX
    Explanations

    references to government control and censorship over communication channels

    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
    ãĥ©ãĤ¹
    -0.08
    ÙħÙĪ
    -0.07
     درب
    -0.07
    .TextInput
    -0.07
     stim
    -0.07
    _ARCH
    -0.07
     trillion
    -0.07
    ippets
    -0.07
    aned
    -0.06
     scand
    -0.06
    POSITIVE LOGITS
     block
    0.08
    :block
    0.07
    blocks
    0.07
     blocked
    0.07
    krom
    0.07
     content
    0.06
    olle
    0.06
     BLOCK
    0.06
     censorship
    0.06
    -block
    0.06
    Activations Density 0.010%

    No Known Activations