© 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. 15-LLAMASCOPE-RES-131K
    11. 103814
    Prev
    Next
    INDEX
    Explanations

    phrases and prompts related to warnings and spoilers regarding content

    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
    vero
    -0.07
    ãĥ«ãĤ¯
    -0.06
    quete
    -0.06
     Surveillance
    -0.06
     mon
    -0.06
     Whe
    -0.06
     map
    -0.06
     Jar
    -0.06
    idden
    -0.06
    оÑĢе
    -0.06
    POSITIVE LOGITS
    λεÏħ
    0.07
    üb
    0.07
    /umd
    0.07
    лÑİб
    0.07
     пÑĥ
    0.06
     sque
    0.06
    ÐĽÐŀ
    0.06
    unas
    0.06
     dela
    0.06
    loan
    0.06
    Activations Density 0.005%

    No Known Activations