© 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. 89973
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences or feelings of belonging

    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
    olar
    -0.07
    enza
    -0.06
    evin
    -0.06
    utsch
    -0.06
    entine
    -0.06
    uze
    -0.06
    urette
    -0.06
    仲
    -0.06
    jac
    -0.06
    ÙĨدر
    -0.06
    POSITIVE LOGITS
     –↵↵
    0.07
    URLException
    0.07
    oyer
    0.06
    Storyboard
    0.06
    edenÃŃ
    0.06
    cü
    0.06
    ament
    0.06
     crem
    0.06
    Warnings
    0.06
    Browsable
    0.06
    Activations Density 0.000%

    No Known Activations