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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3370
    Prev
    Next
    INDEX
    Explanations

    phrases related to crime statistics and safety concerns

    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
    ><![
    -0.07
     âĹĦ
    -0.07
     Affero
    -0.06
    llvm
    -0.06
    ÃŃst
    -0.06
     Downs
    -0.06
    pron
    -0.06
     lor
    -0.06
    ONT
    -0.06
    uso
    -0.06
    POSITIVE LOGITS
     record
    0.09
     trends
    0.09
     statistics
    0.09
     stats
    0.09
     Trends
    0.09
    record
    0.08
    .stat
    0.08
     statist
    0.08
     recorded
    0.08
     trend
    0.08
    Activations Density 0.034%

    No Known Activations