© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 107109
    Prev
    Next
    INDEX
    Explanations

    details related to injuries or fatalities resulting from violent incidents

    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
    åIJ§
    -0.07
    éĦ
    -0.06
    /tty
    -0.06
    ickest
    -0.06
     Duy
    -0.06
     tube
    -0.06
    컨
    -0.06
    pton
    -0.06
    istra
    -0.06
    ettle
    -0.06
    POSITIVE LOGITS
     indicating
    0.10
    说æĺİ
    0.09
    suggest
    0.09
     indica
    0.09
    表示
    0.08
     indicates
    0.08
     indicate
    0.08
     indication
    0.08
     suggesting
    0.08
    indic
    0.08
    Activations Density 0.044%

    No Known Activations