© 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. 104302
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and related expressions indicating personal experience or actions

    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
    ignum
    -0.07
    anmar
    -0.07
    ürger
    -0.07
    AGMA
    -0.07
     Herb
    -0.06
    ads
    -0.06
    sburgh
    -0.06
    ONGL
    -0.06
    _SUFFIX
    -0.06
     Flight
    -0.06
    POSITIVE LOGITS
     similar
    0.06
     solved
    0.06
     rout
    0.06
    ilit
    0.06
     answer
    0.06
    amik
    0.06
    kea
    0.06
    à¹ģà¸ģ
    0.06
    :checked
    0.06
     personally
    0.06
    Activations Density 0.003%

    No Known Activations