© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 75713
    Prev
    Next
    INDEX
    Explanations

    third-person pronouns, particularly "they" and "he"

    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
    uden
    -0.07
     �
    -0.06
     Sax
    -0.06
     Advance
    -0.06
    (the
    -0.06
     themselves
    -0.06
    233
    -0.05
    type
    -0.05
     Rebel
    -0.05
    the
    -0.05
    POSITIVE LOGITS
    storybook
    0.09
    soon
    0.08
    _wo
    0.07
     Ñģел
    0.07
    zes
    0.07
    apist
    0.07
    ekt
    0.07
    currentColor
    0.07
    ytt
    0.07
    bsite
    0.07
    Activations Density 0.046%

    No Known Activations