© 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. 104958
    Prev
    Next
    INDEX
    Explanations

    occurrences of the pronouns "I" and "O"

    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
    象
    -0.08
    #:
    -0.07
    اÙĪÙĨد
    -0.07
    .documentation
    -0.07
    istant
    -0.07
    ëĭ´
    -0.07
    ηÏĤ
    -0.07
    ãĥĸãĥª
    -0.06
    à¥įâĢį
    -0.06
    СТ
    -0.06
    POSITIVE LOGITS
    asm
    0.07
    ema
    0.06
    IIIK
    0.06
    yw
    0.06
     Applied
    0.06
    gamber
    0.06
    sch
    0.06
    esk
    0.06
    zelf
    0.06
    iasm
    0.06
    Activations Density 0.006%

    No Known Activations