© 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. 124706
    Prev
    Next
    INDEX
    Explanations

    phrases indicating hopefulness and personal assurance

    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
    _HDR
    -0.08
     vir
    -0.07
    æ²¢
    -0.07
     dó
    -0.06
    inker
    -0.06
     tvar
    -0.06
    vir
    -0.06
     evet
    -0.06
    INA
    -0.06
     pul
    -0.06
    POSITIVE LOGITS
     above
    0.12
     Above
    0.11
    above
    0.10
     foregoing
    0.10
    Above
    0.10
    以ä¸Ĭ
    0.10
     hopefully
    0.09
     ABOVE
    0.09
     Hopefully
    0.08
    Hopefully
    0.08
    Activations Density 0.024%

    No Known Activations