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. 5159
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to law enforcement actions

    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
     escaping
    -0.07
    å¼ĺ
    -0.07
    被
    -0.07
     escape
    -0.07
    aft
    -0.07
    Quit
    -0.06
     Escape
    -0.06
    912
    -0.06
    .live
    -0.06
    escape
    -0.06
    POSITIVE LOGITS
     imprison
    0.10
     tá»ĭch
    0.08
     pun
    0.08
     charging
    0.08
     suspend
    0.08
    pun
    0.07
     confisc
    0.07
     deport
    0.07
     extrad
    0.07
     punishing
    0.07
    Activations Density 0.057%

    No Known Activations