© 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. 93075
    Prev
    Next
    INDEX
    Explanations

    discussions about the nature of reality and societal structures

    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
    /TT
    -0.07
    Ïģιά
    -0.07
    ÅĻen
    -0.07
    STR
    -0.06
    udu
    -0.06
    nde
    -0.06
    Ï
    -0.06
    oice
    -0.06
    680
    -0.06
    iyi
    -0.06
    POSITIVE LOGITS
     situation
    0.10
     reality
    0.09
     things
    0.09
     arrangement
    0.08
     situations
    0.08
     affairs
    0.08
     arrangements
    0.08
     Situation
    0.08
     Things
    0.08
     Reality
    0.08
    Activations Density 0.061%

    No Known Activations