© 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 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. 89109
    Prev
    Next
    INDEX
    Explanations

    phrases that involve judgment and conclusions about others

    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
    QA
    -0.08
    qa
    -0.07
    ùi
    -0.06
    æľĽ
    -0.06
     teb
    -0.06
    endir
    -0.06
    ÙĪÙĨا
    -0.06
     Successfully
    -0.06
     Priority
    -0.06
    (strpos
    -0.06
    POSITIVE LOGITS
     assumptions
    0.10
     assumption
    0.09
     assumed
    0.09
     judgment
    0.09
     judgement
    0.08
     dismissal
    0.08
     jud
    0.08
     judgments
    0.08
     discount
    0.08
     premature
    0.07
    Activations Density 0.048%

    No Known Activations