© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 42809
    Prev
    Next
    INDEX
    Explanations

    elements related to artistic and creative works

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    iffies
    -0.08
    kuk
    -0.08
    593
    -0.07
    owitz
    -0.07
    omit
    -0.07
    ugins
    -0.07
     Exercise
    -0.06
    ình
    -0.06
    eed
    -0.06
    alars
    -0.06
    POSITIVE LOGITS
     writings
    0.10
    presence
    0.09
     career
    0.09
     candidacy
    0.09
     reign
    0.09
     presence
    0.09
     careers
    0.08
     contributions
    0.08
     obra
    0.07
     talents
    0.07
    Activations Density 0.178%

    No Known Activations