© 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. 2964
    Prev
    Next
    INDEX
    Explanations

    themes related to danger or hazardous conditions

    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
     поÑĪ
    -0.07
     Invasion
    -0.07
    weak
    -0.06
    Weak
    -0.06
    eft
    -0.06
    pector
    -0.06
    ovice
    -0.06
    ozor
    -0.06
     Weak
    -0.06
    .setViewport
    -0.06
    POSITIVE LOGITS
     dangerous
    0.17
     dangers
    0.15
     danger
    0.15
    danger
    0.14
    -danger
    0.13
     Dangerous
    0.13
     hazardous
    0.12
     опаÑģ
    0.11
    Danger
    0.11
     Danger
    0.11
    Activations Density 0.159%

    No Known Activations