© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 70889
    Prev
    Next
    INDEX
    Explanations

    installation-related commands and package management keywords

    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
    moth
    -0.07
     PhpStorm
    -0.06
    arkan
    -0.06
     authDomain
    -0.06
    efe
    -0.06
    rug
    -0.06
    lectric
    -0.06
    รà¸ģ
    -0.06
    585
    -0.06
    POSITIVE LOGITS
     Mori
    0.07
     Mou
    0.07
     Khu
    0.07
    enance
    0.07
    æģ¯
    0.06
    .capture
    0.06
    ombat
    0.06
    -dev
    0.06
    uhn
    0.06
    ê·¼
    0.06
    Activations Density 0.003%

    No Known Activations