© 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. 82666
    Prev
    Next
    INDEX
    Explanations

    phrases indicating collaborative efforts or processes aimed at improving security

    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
    .liferay
    -0.08
    ezi
    -0.08
    isté
    -0.08
    .Listener
    -0.07
    .scalablytyped
    -0.07
    Îŀ
    -0.07
    incinn
    -0.07
    گاب
    -0.07
    Normalization
    -0.07
    ÙĨÚ¯
    -0.07
    POSITIVE LOGITS
     Privacy
    0.09
     privacy
    0.08
     opt
    0.07
    Privacy
    0.07
    ianne
    0.06
     default
    0.06
    privacy
    0.06
     defaults
    0.06
     baked
    0.06
     Cop
    0.06
    Activations Density 0.001%

    No Known Activations