© 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. 57856
    Prev
    Next
    INDEX
    Explanations

    references to "citizens" and "cybercrime" in various formats

    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
    urent
    -0.07
     Yuan
    -0.06
    edo
    -0.06
    holds
    -0.06
    edly
    -0.06
    ziej
    -0.06
    edb
    -0.06
    çĶ°
    -0.06
    edList
    -0.06
    bias
    -0.06
    POSITIVE LOGITS
    zens
    0.10
    izens
    0.09
    rus
    0.09
    izen
    0.09
    adel
    0.08
    ernes
    0.08
    ocos
    0.07
    rape
    0.07
    scape
    0.07
    à¸ŀล
    0.07
    Activations Density 0.010%

    No Known Activations