© 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 EvalsExportsinterp-engineNEWAPI 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. 5161
    Prev
    Next
    INDEX
    Explanations

    numerical values and financial data

    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
    acco
    -0.07
    iga
    -0.07
     hrom
    -0.07
     Hein
    -0.07
    434
    -0.07
    roe
    -0.07
    ieee
    -0.07
    reste
    -0.06
    enta
    -0.06
    273
    -0.06
    POSITIVE LOGITS
    hyp
    0.06
    iors
    0.06
    cker
    0.06
    izador
    0.06
    kest
    0.06
    /tos
    0.06
    ingles
    0.06
     temporarily
    0.06
     hipp
    0.06
    etler
    0.06
    Activations Density 0.005%

    No Known Activations