© 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. 5-LLAMASCOPE-RES-131K
    11. 125888
    Prev
    Next
    INDEX
    Explanations

    phrases related to the regulation and enforcement of rules or laws

    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
    chts
    -0.07
     addCriterion
    -0.06
    Delayed
    -0.06
    ego
    -0.06
    ÄįÃŃ
    -0.06
    imson
    -0.06
    èį
    -0.06
    avit
    -0.06
     McGu
    -0.06
     numberOfRowsInSection
    -0.06
    POSITIVE LOGITS
    ifecycle
    0.07
    tight
    0.07
    éĢļéģİ
    0.07
     tighter
    0.06
    ãĥ¬ãĥ³
    0.06
    assa
    0.06
    áºŃu
    0.06
    rottle
    0.06
    atable
    0.06
    uggle
    0.06
    Activations Density 0.004%

    No Known Activations