© 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. 89051
    Prev
    Next
    INDEX
    Explanations

    phrases related to child and pet welfare

    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
    LES
    -0.07
    .scalablytyped
    -0.07
    ASF
    -0.07
    ä¹ĭä¸Ģ
    -0.07
    ̣
    -0.07
    aggio
    -0.07
    agoon
    -0.07
    ouver
    -0.07
    äl
    -0.07
    à¹ij
    -0.07
    POSITIVE LOGITS
    's
    0.09
    ’s
    0.08
    ův
    0.07
    mie
    0.06
    (s
    0.06
    们
    0.06
    åĢij
    0.06
    /part
    0.06
     Zu
    0.06
     Brill
    0.06
    Activations Density 0.013%

    No Known Activations