© 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. 70983
    Prev
    Next
    INDEX
    Explanations

    snippets of code or programming elements

    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
    phia
    -0.07
    èĴĻ
    -0.07
    andle
    -0.07
    ICT
    -0.06
    phas
    -0.06
     Bolt
    -0.06
    åĸ
    -0.06
    ÙĪÙĦات
    -0.06
    bolt
    -0.06
    anch
    -0.06
    POSITIVE LOGITS
     DataRow
    0.08
     ListViewItem
    0.08
    ippi
    0.07
     ListItem
    0.07
    cles
    0.07
    ListItem
    0.07
    Touchable
    0.06
    irth
    0.06
    .li
    0.06
     ListTile
    0.06
    Activations Density 0.019%

    No Known Activations