© 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. 107161
    Prev
    Next
    INDEX
    Explanations

    words related to artistic expression or creative works

    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
    .serial
    -0.06
    èª
    -0.06
    uli
    -0.06
    atri
    -0.06
    инов
    -0.06
    алÑĥ
    -0.06
    üstü
    -0.06
    à¹Īาม
    -0.06
    ourd
    -0.06
    opak
    -0.06
    POSITIVE LOGITS
     verb
    0.09
     verbs
    0.08
    .qq
    0.07
    ÏĩÏİ
    0.07
    ieren
    0.07
    Verb
    0.07
    ÑģÑĮ
    0.07
     tiener
    0.06
    743
    0.06
    ò
    0.06
    Activations Density 0.042%

    No Known Activations