© 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. 87539
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of artistic expression

    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
    ût
    -0.07
    ubo
    -0.06
    ieri
    -0.06
    udad
    -0.06
     Lowe
    -0.06
     Casino
    -0.06
    fork
    -0.06
    ientes
    -0.06
    èle
    -0.06
     chol
    -0.06
    POSITIVE LOGITS
    _PRI
    0.07
     ready
    0.07
    osten
    0.06
    FC
    0.06
    iser
    0.06
    érc
    0.06
    _RC
    0.06
     Regents
    0.06
     fc
    0.06
     FC
    0.06
    Activations Density 0.000%

    No Known Activations