© 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. 61499
    Prev
    Next
    INDEX
    Explanations

    concepts related to breaking societal norms and barriers

    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
    lix
    -0.08
    rana
    -0.06
    éĻĦ
    -0.06
    ToDevice
    -0.06
    addin
    -0.06
    isas
    -0.06
    iero
    -0.06
    .GroupLayout
    -0.06
     phụ
    -0.06
    rix
    -0.06
    POSITIVE LOGITS
     altogether
    0.06
    ëĮĢë¡ľ
    0.06
    yon
    0.06
    Mahon
    0.06
     viol
    0.06
     Simmons
    0.06
     simult
    0.06
    -breaking
    0.06
    ims
    0.06
     restr
    0.06
    Activations Density 0.017%

    No Known Activations