© 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. 9-LLAMASCOPE-RES-131K
    11. 97588
    Prev
    Next
    INDEX
    Explanations

    references to unique or customized products and modifications

    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
    asty
    -0.08
    quia
    -0.07
    ohana
    -0.07
    ochrome
    -0.07
    ayer
    -0.07
    .metro
    -0.07
    rire
    -0.07
    oyo
    -0.07
    lu
    -0.06
    nga
    -0.06
    POSITIVE LOGITS
    ÑĤоÑĤ
    0.06
    adel
    0.06
    ibase
    0.06
     Rena
    0.06
    373
    0.06
    воÑİ
    0.06
     bases
    0.06
    ama
    0.06
     Jennings
    0.06
     inputs
    0.05
    Activations Density 0.004%

    No Known Activations