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

    Neuronpedia

    Jacobian LensNEW
    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. 88459
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal experiences and perspectives

    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
    ıklı
    -0.07
    /=
    -0.07
    екаÑĢ
    -0.07
    readcr
    -0.07
    иÑĩа
    -0.07
    igated
    -0.07
     ÙĨÛĮر
    -0.07
    kı
    -0.07
    TabIndex
    -0.07
    jmu
    -0.07
    POSITIVE LOGITS
    _exempt
    0.07
    .RowStyle
    0.06
    NS
    0.06
     Lexer
    0.06
    410
    0.06
    etik
    0.06
     Hamp
    0.06
     hel
    0.06
    anium
    0.06
     Bund
    0.06
    Activations Density 0.068%

    No Known Activations