© 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. 76343
    Prev
    Next
    INDEX
    Explanations

    references to government or regulatory organizations and their associated activities

    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
     Mil
    -0.06
     Mou
    -0.06
    uyo
    -0.06
    529
    -0.06
    lique
    -0.06
     Kling
    -0.06
    еÑĤÑĥ
    -0.06
    edl
    -0.06
    zano
    -0.06
     Gian
    -0.06
    POSITIVE LOGITS
     excer
    0.06
     thu
    0.06
    ÏĮδ
    0.06
    ÌĨ
    0.06
    abb
    0.06
    ÏĦÏİ
    0.06
    پس
    0.06
     FOREIGN
    0.06
    Ñģклад
    0.06
    .rad
    0.06
    Activations Density 0.012%

    No Known Activations