Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5242
    Prev
    Next
    INDEX
    Explanations

    HTML and JavaScript operations related to modifying and displaying content in a web application

    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
     Gregg
    -0.07
    647
    -0.06
     IPPROTO
    -0.06
    397
    -0.06
    377
    -0.06
    à¸Ĺย
    -0.06
     Greg
    -0.06
    eldon
    -0.06
    zn
    -0.05
    737
    -0.05
    POSITIVE LOGITS
     '<
    0.13
    '<
    0.11
     `<
    0.11
     "<
    0.11
     html
    0.10
    ='<
    0.10
     Html
    0.09
    "<
    0.09
     HTML
    0.09
    ('<
    0.09
    Activations Density 0.025%

    No Known Activations