© 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. 58681
    Prev
    Next
    INDEX
    Explanations

    references to social gatherings and communal experiences

    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
     ÄĮer
    -0.07
    endencies
    -0.06
     Bik
    -0.06
    ebi
    -0.06
    _irq
    -0.06
    æ¿
    -0.06
    MBER
    -0.06
    rou
    -0.06
     nebu
    -0.06
     lineno
    -0.06
    POSITIVE LOGITS
     è±
    0.07
    éŁ³æ¥½
    0.07
    .Mobile
    0.07
    throp
    0.07
     party
    0.07
     pre
    0.07
     preg
    0.06
     parties
    0.06
    ackages
    0.06
     car
    0.06
    Activations Density 0.002%

    No Known Activations