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

    Neuronpedia

    Jacobian LensNEW
    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. 40356
    Prev
    Next
    INDEX
    Explanations

    references to control and censorship of information

    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
    ubl
    -0.08
    ÑĢаÑģ
    -0.07
    ovit
    -0.07
    ozo
    -0.07
    gnore
    -0.07
    μι
    -0.07
    arih
    -0.06
    weis
    -0.06
    EMY
    -0.06
    hir
    -0.06
    POSITIVE LOGITS
     freedom
    0.09
     fre
    0.09
     censorship
    0.08
     freely
    0.08
     regime
    0.08
     Freedom
    0.08
     forbidden
    0.07
     freedoms
    0.07
    fre
    0.07
     underground
    0.07
    Activations Density 0.057%

    No Known Activations