© 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. 85941
    Prev
    Next
    INDEX
    Explanations

    concepts related to artistic expression and influence

    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
    antis
    -0.07
    rompt
    -0.07
    bian
    -0.07
    ãģ®åŃIJ
    -0.07
    çļĦæĥħ
    -0.06
    znik
    -0.06
    çļĦæīĭ
    -0.06
    zure
    -0.06
    ’s
    -0.06
    imb
    -0.06
    POSITIVE LOGITS
     samt
    0.07
    decorators
    0.07
     whom
    0.07
    ï¼Į以åıĬ
    0.06
    Msp
    0.06
    337
    0.06
    his
    0.06
    enan
    0.06
    hoot
    0.06
    以åıĬ
    0.06
    Activations Density 0.212%

    No Known Activations