© 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. 17-LLAMASCOPE-RES-131K
    11. 75534
    Prev
    Next
    INDEX
    Explanations

    concepts related to safeguarding and storing valuable items or information

    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
    онÑĮ
    -0.08
    æī¶
    -0.08
    DebugEnabled
    -0.07
    ousel
    -0.07
    domains
    -0.07
    Ws
    -0.07
    chet
    -0.07
    OFFSET
    -0.07
    _Tis
    -0.07
    jit
    -0.07
    POSITIVE LOGITS
     storage
    0.12
     storing
    0.11
     Storage
    0.10
     safe
    0.10
     security
    0.10
    -storage
    0.10
    storage
    0.09
     Security
    0.09
     store
    0.08
     stored
    0.08
    Activations Density 0.011%

    No Known Activations