© 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. 87359
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and database schema

    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
    ipo
    -0.07
    ost
    -0.07
    ifu
    -0.06
     BÃŃ
    -0.06
    .conditions
    -0.06
    vara
    -0.06
    olic
    -0.06
    npj
    -0.06
    uteur
    -0.06
    ải
    -0.06
    POSITIVE LOGITS
     Ridley
    0.06
    sam
    0.06
    tridge
    0.06
    ãĥ£
    0.06
     defaultCenter
    0.06
    ÙĪر
    0.06
    hurst
    0.06
    iffe
    0.06
    bone
    0.06
    oley
    0.06
    Activations Density 0.000%

    No Known Activations