© 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. 54808
    Prev
    Next
    INDEX
    Explanations

    conversational phrases that indicate personal experiences or opinions

    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
    ignet
    -0.07
    neau
    -0.07
    gmt
    -0.07
     pÅĻitom
    -0.07
    fuck
    -0.07
    noch
    -0.07
     wiÄĻc
    -0.06
     ÑĤакими
    -0.06
     khung
    -0.06
    дн
    -0.06
    POSITIVE LOGITS
     sometimes
    0.06
    unnel
    0.06
    uma
    0.06
     often
    0.06
    ades
    0.06
     every
    0.06
     Maver
    0.05
     Juliet
    0.05
     another
    0.05
     Cove
    0.05
    Activations Density 0.010%

    No Known Activations