© 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. 9-LLAMASCOPE-RES-131K
    11. 95641
    Prev
    Next
    INDEX
    Explanations

    references to numerical data and statistics related to medical or scientific studies

    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
    186
    -0.07
    ity
    -0.06
     g
    -0.06
    essional
    -0.06
     -
    -0.06
    romo
    -0.05
    owe
    -0.05
    riel
    -0.05
    -
    -0.05
    ppy
    -0.05
    POSITIVE LOGITS
     luder
    0.10
    /goto
    0.08
    Uvs
    0.08
     prostituer
    0.07
    ÃĹ↵↵
    0.07
     fetisch
    0.07
    .cls
    0.07
    ffset
    0.07
     fkk
    0.07
    ê³
    0.07
    Activations Density 0.014%

    No Known Activations