Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5253
    Prev
    Next
    INDEX
    Explanations

    occurrences of arrests related to illegal drug operations

    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
     assassin
    -0.07
     homic
    -0.06
     nederland
    -0.06
     enthusi
    -0.06
     oppon
    -0.06
     assail
    -0.06
     Thief
    -0.06
    ATALOG
    -0.06
     Theft
    -0.06
    chos
    -0.06
    POSITIVE LOGITS
     Operation
    0.16
     operation
    0.15
     raids
    0.15
    Operation
    0.14
     raid
    0.14
    operation
    0.13
     bust
    0.13
     arrests
    0.13
    raid
    0.12
    -operation
    0.12
    Activations Density 0.065%

    No Known Activations