© 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. 118772
    Prev
    Next
    INDEX
    Explanations

    references to artistic expressions and creative achievements

    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
    λμ
    -0.06
     Elementary
    -0.06
     Hatch
    -0.06
    atee
    -0.06
    FFE
    -0.06
    ÎŃÏģγ
    -0.06
     Julius
    -0.06
    PEnd
    -0.06
    olicit
    -0.05
    lectic
    -0.05
    POSITIVE LOGITS
     high
    0.11
     haut
    0.10
     sophisticated
    0.10
     elite
    0.10
     elit
    0.10
     VIP
    0.10
     sophistication
    0.10
    (high
    0.09
     luxury
    0.09
    ãĢģé«ĺ
    0.09
    Activations Density 0.001%

    No Known Activations