© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 104271
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the importance of evidence and specific details

    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
    -Semit
    -0.08
    uptools
    -0.08
     íĮĮìĿ¼ì²¨ë¶Ģ
    -0.07
    owski
    -0.07
     jspb
    -0.07
    styleType
    -0.07
    ázi
    -0.07
    forman
    -0.07
    umen
    -0.07
    InterfaceOrientation
    -0.07
    POSITIVE LOGITS
    0.06
    asin
    0.06
     precursor
    0.06
    ad
    0.06
     narr
    0.05
     Favor
    0.05
    ardon
    0.05
    affiliate
    0.05
     bias
    0.05
    ÑĥÑģлов
    0.05
    Activations Density 0.582%

    No Known Activations