© 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. 93989
    Prev
    Next
    INDEX
    Explanations

    references to execution-related concepts and practices

    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
     harassing
    -0.07
    alach
    -0.07
    911
    -0.06
     çal
    -0.06
    934
    -0.06
     subpoena
    -0.06
     primaries
    -0.06
    AP
    -0.06
    Ïģα
    -0.06
    502
    -0.06
    POSITIVE LOGITS
     execution
    0.12
    execution
    0.10
     Execution
    0.10
     executions
    0.10
     death
    0.10
    hang
    0.10
    Execution
    0.09
     executed
    0.09
     hang
    0.08
     execute
    0.08
    Activations Density 0.053%

    No Known Activations