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. 9-LLAMASCOPE-RES-131K
    6. 95646
    Prev
    Next
    INDEX
    Explanations

    references to specific iPhone models

    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
    .scalablytyped
    -0.07
    DevExpress
    -0.07
    WebHost
    -0.07
     à¹Ĩ
    -0.07
    iple
    -0.07
    ëį°
    -0.06
    annya
    -0.06
     tu
    -0.06
    à¹Ĩ
    -0.06
    edly
    -0.06
    POSITIVE LOGITS
    $__
    0.07
     Siz
    0.06
    ushi
    0.06
     storyboard
    0.06
    strap
    0.06
     nhiên
    0.06
    QQ
    0.06
    lish
    0.06
     Farrell
    0.06
    ROP
    0.06
    Activations Density 0.002%

    No Known Activations