© 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 EvalsExportsinterp-engineNEWAPI 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. 31135
    Prev
    Next
    INDEX
    Explanations

    phrases related to events following significant occurrences or changes

    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
    á»ĥ
    -0.07
    iÄįka
    -0.06
    icas
    -0.06
     ÑĤам
    -0.06
    ãģªãĤĵãģ¦
    -0.06
    .tc
    -0.06
    ãģĿãģ®
    -0.06
    æīĭãĤĴ
    -0.06
    -translate
    -0.06
    ÙĦÙĦ
    -0.06
    POSITIVE LOGITS
     recently
    0.15
     recent
    0.14
    recent
    0.12
     earlier
    0.12
    Recently
    0.10
     lately
    0.09
     elsewhere
    0.09
     similarly
    0.09
     another
    0.09
     Recently
    0.09
    Activations Density 0.020%

    No Known Activations