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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 75093
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to safeguarding and 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
    _defs
    -0.08
    azio
    -0.07
    hood
    -0.07
    onde
    -0.07
    еÑģÑĤи
    -0.07
    icz
    -0.07
    Ý
    -0.07
    Ì
    -0.07
     Dann
    -0.07
    ERGE
    -0.07
    POSITIVE LOGITS
     against
    0.13
    against
    0.10
     Against
    0.09
    ively
    0.09
    Against
    0.08
     interests
    0.08
     vulnerable
    0.08
     tegen
    0.08
     itself
    0.07
     fragile
    0.07
    Activations Density 0.016%

    No Known Activations