© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 89422
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to safeguarding and containment

    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
    ledon
    -0.07
    Ì
    -0.07
    Ý
    -0.07
    aiser
    -0.06
    hop
    -0.06
    otine
    -0.06
    еÑģÑĤи
    -0.06
    inear
    -0.06
    Ø®ÛĮ
    -0.06
    _defs
    -0.06
    POSITIVE LOGITS
     against
    0.12
    against
    0.09
    Against
    0.08
     Against
    0.08
     vulnerable
    0.08
     us
    0.07
     sensitive
    0.07
     itself
    0.07
    ively
    0.07
    -sensitive
    0.06
    Activations Density 0.022%

    No Known Activations