© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57534
    Prev
    Next
    INDEX
    Explanations

    instances of particular subjects and their activities or events

    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
     eventual
    -0.07
     Kirst
    -0.06
    нÑĸÑģÑĤ
    -0.06
    mn
    -0.06
     squeez
    -0.06
    ÑĢоÑģÑĤ
    -0.06
     unlike
    -0.06
    Ł¥
    -0.06
     dÄ±ÅŁÄ±nda
    -0.06
     Chapman
    -0.06
    POSITIVE LOGITS
     another
    0.20
     similarly
    0.17
    another
    0.17
     equally
    0.15
    åı¦ä¸Ģ
    0.14
    Another
    0.14
     Another
    0.14
    åı¦
    0.13
     otro
    0.12
     ëĺIJ
    0.12
    Activations Density 0.035%

    No Known Activations