© 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. 9-LLAMASCOPE-RES-131K
    11. 94221
    Prev
    Next
    INDEX
    Explanations

    mentions of museum exhibitions and related content

    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
    ity
    -0.06
    ikal
    -0.06
     Cristiano
    -0.06
     Howell
    -0.06
    _HEAP
    -0.05
     Canter
    -0.05
     performances
    -0.05
    æ·»
    -0.05
    613
    -0.05
    agrid
    -0.05
    POSITIVE LOGITS
    aña
    0.07
    ERRU
    0.07
    SYNC
    0.07
    alien
    0.07
    bcm
    0.07
    enze
    0.07
    UPLE
    0.07
    ojÃŃ
    0.06
    imals
    0.06
    TypeError
    0.06
    Activations Density 0.017%

    No Known Activations