© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 120181
    Prev
    Next
    INDEX
    Explanations

    personal pronouns indicating relationships and address

    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
    воÑİ
    -0.08
    erville
    -0.07
    apter
    -0.07
     rozs
    -0.07
    оÑĩно
    -0.07
    ĽĦ
    -0.07
    MSN
    -0.07
    âĢĮاÙĨ
    -0.07
    öst
    -0.07
    ëĭĪ
    -0.07
    POSITIVE LOGITS
    ots
    0.06
     to
    0.06
    /us
    0.06
    bers
    0.06
    ê
    0.06
    amm
    0.05
     Elig
    0.05
    aes
    0.05
    bert
    0.05
    ä¹IJ
    0.05
    Activations Density 0.015%

    No Known Activations