© 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. 69833
    Prev
    Next
    INDEX
    Explanations

    references to committees and processes related to awards and nominations

    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
    anik
    -0.07
    _regularizer
    -0.07
     âĹĦ
    -0.07
     prevState
    -0.07
    èn
    -0.07
    fik
    -0.07
    ABL
    -0.07
    γοÏħ
    -0.06
    ADI
    -0.06
    äge
    -0.06
    POSITIVE LOGITS
    utan
    0.07
     giz
    0.06
    Singleton
    0.06
     blind
    0.06
     crit
    0.06
     evaluation
    0.06
    usp
    0.06
     scre
    0.06
    eval
    0.06
     secret
    0.06
    Activations Density 0.008%

    No Known Activations