© 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. 16165
    Prev
    Next
    INDEX
    Explanations

    nostalgic references to past experiences or eras

    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
    ince
    -0.06
     McLaren
    -0.06
     Cair
    -0.06
     Sculpt
    -0.06
     prod
    -0.05
     marvel
    -0.05
    umbnails
    -0.05
     WARRANTY
    -0.05
    engeance
    -0.05
    rap
    -0.05
    POSITIVE LOGITS
     vintage
    0.16
     Vintage
    0.14
     retro
    0.14
    Vintage
    0.13
     Retro
    0.12
     antique
    0.11
     old
    0.10
     antiqu
    0.10
    intage
    0.10
    åı¤
    0.10
    Activations Density 0.109%

    No Known Activations