© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 88023
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the founding of organizations or companies

    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
    osg
    -0.08
    wj
    -0.08
    Bounding
    -0.08
    iland
    -0.08
    utan
    -0.08
    elay
    -0.07
    reste
    -0.07
    (ع
    -0.07
    оÑģÑĢед
    -0.07
    ieve
    -0.07
    POSITIVE LOGITS
    199
    0.07
     partnership
    0.07
    200
    0.07
    198
    0.06
    192
    0.06
    mom
    0.05
    197
    0.05
     Partnership
    0.05
     partnerships
    0.05
     عاÙħ
    0.05
    Activations Density 0.010%

    No Known Activations