© 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. 104679
    Prev
    Next
    INDEX
    Explanations

    instances of the pronouns "I," "we," and "they."

    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
    uggy
    -0.07
    rax
    -0.07
    ساÙĨÛĮ
    -0.07
    589
    -0.07
    ög
    -0.07
    andas
    -0.06
    OfString
    -0.06
    ŀæĢ§
    -0.06
    leness
    -0.06
    çĪµ
    -0.06
    POSITIVE LOGITS
     fasc
    0.06
    kiye
    0.06
    ars
    0.06
    nap
    0.06
     adv
    0.06
     scre
    0.05
     Sec
    0.05
    ekler
    0.05
    Enumerable
    0.05
    aven
    0.05
    Activations Density 0.021%

    No Known Activations