© 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. 119265
    Prev
    Next
    INDEX
    Explanations

    key names and terms related to societal commentary and critique

    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
    odo
    -0.10
     understandably
    -0.08
    ãģłãĤįãģĨ
    -0.07
    ODO
    -0.06
     mÃ¼ÅŁ
    -0.06
     alone
    -0.06
    avenport
    -0.06
    ,...↵↵
    -0.06
    arga
    -0.06
    ноÑĩ
    -0.06
    POSITIVE LOGITS
     actually
    0.26
    actually
    0.22
     Actually
    0.21
    Actually
    0.19
     actual
    0.18
    å®ŀéĻħ
    0.17
     aslında
    0.15
    åħ¶å®ŀ
    0.15
    actual
    0.15
     reality
    0.15
    Activations Density 0.008%

    No Known Activations