© 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. 28676
    Prev
    Next
    INDEX
    Explanations

    mentions of ransomware and related terms

    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
    \views
    -0.07
    laws
    -0.06
    eken
    -0.06
    rix
    -0.06
    ologia
    -0.06
    .pub
    -0.06
    logfile
    -0.06
    ÑĥÑĢн
    -0.06
    令
    -0.06
    .mk
    -0.06
    POSITIVE LOGITS
    iene
    0.08
    atas
    0.07
    aeper
    0.07
    imers
    0.07
    etas
    0.07
    AtA
    0.07
    audi
    0.06
    اÙĦÙĩ
    0.06
    راÙĨÙĩ
    0.06
    ienes
    0.06
    Activations Density 0.001%

    No Known Activations