© 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. 15-LLAMASCOPE-RES-131K
    11. 103623
    Prev
    Next
    INDEX
    Explanations

    punctuation and colloquial language emphasizing dialogue or speech

    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
     Kare
    -0.07
    ãĤ¤ãĤº
    -0.06
    amat
    -0.06
    alar
    -0.06
     Ware
    -0.06
    andin
    -0.06
    á»ĭp
    -0.06
    alet
    -0.06
    ÑĢиз
    -0.06
    é±¼
    -0.06
    POSITIVE LOGITS
     eoq
    0.07
     fetisch
    0.07
     another
    0.07
    ÙĨدر
    0.07
    ospels
    0.07
     geschichten
    0.07
     erotisk
    0.06
    877
    0.06
    olta
    0.06
     naken
    0.06
    Activations Density 0.028%

    No Known Activations