© 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. 1122
    Prev
    Next
    INDEX
    Explanations

    phrases related to data protection and user privacy

    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
    ç«ĭãģ¦
    -0.07
    _ASCII
    -0.07
    asar
    -0.06
    सल
    -0.06
    ÑĦика
    -0.06
     limp
    -0.06
    æŁ³
    -0.06
    仲
    -0.06
    /Branch
    -0.06
     Hund
    -0.06
    POSITIVE LOGITS
     safety
    0.15
     Safety
    0.12
     security
    0.12
    å®īåħ¨
    0.12
    Safety
    0.12
    afety
    0.10
     risk
    0.09
     безопаÑģноÑģÑĤи
    0.09
     protection
    0.09
     privacy
    0.09
    Activations Density 0.060%

    No Known Activations